© 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. 4129
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to notable individuals, brands, or entities

    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
     initComponents
    -0.68
    ymce
    -0.49
    ɵɵelementStart
    -0.45
     boîtier
    -0.42
    behaved
    -0.42
    treasure
    -0.41
    WireFormatLite
    -0.41
    tagext
    -0.40
     bellezza
    -0.40
    AutoScaleMode
    -0.40
    POSITIVE LOGITS
     cement
    0.61
     glue
    0.60
     Glue
    0.59
     swear
    0.55
    Ans
    0.55
     Ans
    0.55
    makeConstraints
    0.54
     oath
    0.53
     vow
    0.52
    Glue
    0.52
    Activations Density 0.591%

    No Known Activations