© 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. 40-GEMMASCOPE-RES-16K
    6. 1966
    Prev
    Next
    INDEX
    Explanations

    specific positioning or placement details in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThemeOverlay
    -0.54
    Above
    -0.47
    렷
    -0.46
     Above
    -0.44
    FromNib
    -0.41
     以上
    -0.41
    onOptions
    -0.41
    ByExample
    -0.41
     conseguenza
    -0.40
    horabuena
    -0.40
    POSITIVE LOGITS
     bottom
    1.15
     rear
    0.78
     far
    0.78
    bottom
    0.78
     top
    0.77
     back
    0.77
     underside
    0.76
     opposite
    0.73
     backside
    0.71
     ends
    0.70
    Activations Density 0.632%

    No Known Activations