© 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. 4-GEMMASCOPE-RES-16K
    11. 914
    Prev
    Next
    INDEX
    Explanations

    references to keywords and SEO-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.66
    ch
    -0.63
    k
    -0.61
    maka
    -0.58
    ecap
    -0.58
     proud
    -0.57
    c
    -0.56
    ⓧ
    -0.55
    StrictEqual
    -0.54
    гну
    -0.53
    POSITIVE LOGITS
     keywords
    2.50
     Keywords
    2.41
    Keywords
    2.36
     keyword
    2.33
     Keyword
    2.14
    keywords
    2.11
    keyword
    1.99
    Keyword
    1.99
    KEYWORDS
    1.62
    KEYWORD
    1.58
    Activations Density 0.063%

    No Known Activations