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. 17-GEMMASCOPE-RES-16K
    6. 7177
    Prev
    Next
    INDEX
    Explanations

    terms related to evacuations and emergency responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.63
     AssemblyTitle
    -0.59
     setw
    -0.55
    ArgsConstructor
    -0.54
    IMPORTED
    -0.52
    lež
    -0.51
    moveToFirst
    -0.51
    AddTagHelper
    -0.50
    ByPrimaryKey
    -0.49
     lupa
    -0.48
    POSITIVE LOGITS
     evacuation
    1.33
     evacuate
    1.30
     flee
    1.18
     evacu
    1.16
     evacuated
    1.13
     fleeing
    1.10
     escape
    1.07
     escaping
    0.97
     retreat
    0.96
     evac
    0.95
    Activations Density 0.203%

    No Known Activations