© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3979
    Prev
    Next
    INDEX
    Explanations

    the word "specifically" and its variations, indicating a focus on detailed information or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.56
     المعيارى
    -0.48
    migrationBuilder
    -0.46
    MLLoader
    -0.45
    fortawesome
    -0.44
    ContentLoaded
    -0.44
    izr
    -0.43
     createSlice
    -0.43
    endphp
    -0.43
    ClientRect
    -0.43
    POSITIVE LOGITS
     specifically
    0.92
     precisely
    0.90
    Specifically
    0.88
    specifically
    0.86
     Specifically
    0.84
     specific
    0.84
    Welcome
    0.79
     específicamente
    0.79
    specific
    0.79
     SPECIFIC
    0.79
    Activations Density 0.131%

    No Known Activations