© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5863
    Prev
    Next
    INDEX
    Explanations

    spatial references related to directions and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moeite
    -0.44
     DriverManager
    -0.42
    不成
    -0.41
    WebControls
    -0.40
     Eing
    -0.38
     SEÑ
    -0.37
    restling
    -0.37
     saurait
    -0.36
    CardContent
    -0.36
    comod
    -0.36
    POSITIVE LOGITS
     east
    0.89
     south
    0.84
     north
    0.76
     west
    0.74
     southeast
    0.72
     eastward
    0.67
    south
    0.66
    north
    0.64
     southward
    0.63
     southwest
    0.60
    Activations Density 0.261%

    No Known Activations