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. 20-GEMMASCOPE-RES-16K
    6. 7883
    Prev
    Next
    INDEX
    Explanations

    names and terms related to programming, technology, or computer systems

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

    ending in "ick" or "ack"

    np_acts-logits-general · gemini-2.0-flash

    ick, Hack, Buck, ACK suffixes

    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
    </tfoot>
    -0.66
    erba
    -0.60
    MessageOf
    -0.58
    gehend
    -0.58
    <%=
    -0.58
    ":[{
    -0.58
     vivos
    -0.55
    ViewFeatures
    -0.55
    redients
    -0.55
    okovic
    -0.55
    POSITIVE LOGITS
    ety
    0.81
    ery
    0.76
    les
    0.74
    eting
    0.66
    a
    0.65
    ers
    0.63
    able
    0.60
     lick
    0.59
    LES
    0.59
    els
    0.55
    Activations Density 0.170%

    No Known Activations