© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11476
    Prev
    Next
    INDEX
    Explanations

    programming or code-related terms and constructs.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code snippets and keywords related to programming languages.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quotation marks and parentheses, especially when used for string formatting or concatenation.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Code syntax: punctuation and operators

    np_acts-logits-general · gemini-2.0-flash

    string concatenation with pluses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ioutil
    -0.52
    държа
    -0.48
     defStyleAttr
    -0.48
     Heights
    -0.48
    afat
    -0.48
     Lux
    -0.47
    asjons
    -0.46
    perg
    -0.45
    dorfer
    -0.45
     Gewähr
    -0.45
    POSITIVE LOGITS
    المشاركات
    0.74
     <=",
    0.72
    BorderFactory
    0.70
     CreateTagHelper
    0.70
     +
    0.69
    OGND
    0.69
    elemField
    0.66
     iprot
    0.65
    InjectAttribute
    0.65
     صوتيه
    0.65
    Activations Density 0.055%

    No Known Activations