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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3887
    Prev
    Next
    INDEX
    Explanations

    references to legal terms or codes related to crime and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.61
     surla
    -0.60
    ագրություններ
    -0.58
     كومونز
    -0.53
    Hauteur
    -0.52
    قات
    -0.52
     InputDecoration
    -0.51
    migrationBuilder
    -0.50
    makedirs
    -0.50
     Gert
    -0.49
    POSITIVE LOGITS
     notified
    0.69
     iprot
    0.67
     framed
    0.64
     notifications
    0.60
    framed
    0.60
     Chwiliwch
    0.58
     framing
    0.58
    msgSender
    0.57
     proviso
    0.55
     notification
    0.54
    Activations Density 0.127%

    No Known Activations