© 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. 8182
    Prev
    Next
    INDEX
    Explanations

    instances of the token "<bos>", which indicates the beginning of a sentence or paragraph

    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
    ↵↵
    -0.56
    <eos>
    -0.53
     nahilalakip
    -0.49
    -0.44
    ↵
    -0.40
    寒
    -0.36
     trous
    -0.36
    īg
    -0.32
    ↵↵↵
    -0.31
     continúas
    -0.31
    POSITIVE LOGITS
     betweenstory
    0.87
     GenerationType
    0.78
    featureID
    0.77
    HostException
    0.72
     jadx
    0.70
     ProtoMessage
    0.69
    oredCriteria
    0.66
    tvguidetime
    0.66
     oprot
    0.66
    SharedCtor
    0.65
    Activations Density 0.019%
    No Known Activations