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. 18-GEMMASCOPE-RES-16K
    6. 3153
    Prev
    Next
    INDEX
    Explanations

    negations or expressions indicating disagreement or denial

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

    "No" followed by a problem/matter/target

    np_acts-logits-general · gemini-2.0-flash

    no, no matter, no problem

    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
    migrationBuilder
    -1.27
     AssemblyCulture
    -1.24
     itſelf
    -1.16
     myſelf
    -1.14
     Roskov
    -1.12
     المعيارى
    -1.09
     themſelves
    -1.08
    IsMutable
    -1.07
     himſelf
    -1.07
     saites
    -1.01
    POSITIVE LOGITS
    ,
    0.89
     no
    0.84
     matter
    0.77
     No
    0.77
    No
    0.75
    no
    0.64
     NO
    0.62
     need
    0.58
    a
    0.57
     wonder
    0.56
    Activations Density 0.071%

    No Known Activations