© 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. 18-GEMMASCOPE-RES-16K
    11. 8900
    Prev
    Next
    INDEX
    Explanations

    references to documentation and structuring in programming contexts, particularly related to Java

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

    HTML or Java code block markers

    np_acts-logits-general · gemini-2.0-flash

    blockList structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    &
    -0.50
    fo
    -0.45
    ↵↵
    -0.44
    N
    -0.43
    it
    -0.42
    mit
    -0.41
    my
    -0.40
    ss
    -0.40
    -
    -0.39
    rot
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    2.53
    GEBURTSDATUM
    2.30
    tagHelperRunner
    2.14
    InjectAttribute
    2.12
    expandindo
    2.12
     autorytatywna
    2.11
     nahilalakip
    2.01
    ValueStyle
    1.99
    IntoConstraints
    1.96
     resourceCulture
    1.92
    Activations Density 0.032%

    No Known Activations