© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8891
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and angles in relation to slopes and inclines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onPostExecute
    -0.81
    ruptedException
    -0.71
    Parcelize
    -0.67
    DebuggerNonUser
    -0.63
     anello
    -0.63
     мәгълү
    -0.62
     насељу
    -0.62
     Dunham
    -0.62
    CppCodeGen
    -0.62
    uvo
    -0.61
    POSITIVE LOGITS
     slope
    1.15
     slopes
    1.14
     Slope
    1.02
    Slope
    1.01
     sloping
    0.99
    slope
    0.96
     steeper
    0.95
     incline
    0.85
     steep
    0.84
     inclin
    0.82
    Activations Density 0.284%

    No Known Activations