Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8477
    Prev
    Next
    INDEX
    Explanations

    directional terms indicating movement or positioning

    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
    ఔ
    -0.36
    AnchorStyles
    -0.34
     booties
    -0.34
     getInstance
    -0.33
    ([^
    -0.32
    getInstance
    -0.32
     detalhe
    -0.32
    oneof
    -0.31
    ⓘ
    -0.31
     drizzle
    -0.31
    POSITIVE LOGITS
     upward
    2.72
     downward
    2.55
     outward
    2.52
     inward
    2.47
     forward
    2.33
     downwards
    2.25
     backward
    2.25
     upwards
    2.22
     onward
    2.14
    ward
    2.13
    Activations Density 0.151%

    No Known Activations