© 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. 8102
    Prev
    Next
    INDEX
    Explanations

    references to other documents or sources

    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
     UserManager
    -0.44
    chastic
    -0.42
     buta
    -0.41
    BagLayout
    -0.40
    outState
    -0.38
     blusa
    -0.37
     jakarta
    -0.36
    asgi
    -0.36
     EEA
    -0.36
    vician
    -0.36
    POSITIVE LOGITS
     Ref
    3.98
    Ref
    3.94
     ref
    3.94
    ref
    3.55
     REF
    3.06
    REF
    2.94
     refs
    2.56
     Refs
    2.50
    Refs
    2.48
    refs
    2.22
    Activations Density 0.308%

    No Known Activations