Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 562
    Prev
    Next
    INDEX
    Explanations

    references to legal and institutional responsibilities

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

    Prepositions followed by "by" or "of"

    np_acts-logits-general · gemini-2.0-flash

    by the

    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
    int
    -0.43
    хема
    -0.42
    rens
    -0.41
    spm
    -0.40
    e
    -0.40
    kelig
    -0.39
     alles
    -0.38
    o
    -0.38
    Uint
    -0.36
    ัด
    -0.35
    POSITIVE LOGITS
     resourceCulture
    1.08
    protoimpl
    1.05
     Normdatei
    0.97
     EconPapers
    0.96
    GraphicsUnit
    0.94
     someone
    0.93
     Италијани
    0.92
    Personensuche
    0.92
    帖最后由
    0.90
    someone
    0.90
    Activations Density 0.552%

    No Known Activations