© 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. 8269
    Prev
    Next
    INDEX
    Explanations

    references to chambers, particularly in political or orchestral contexts

    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
    WebElementEntity
    -0.59
    ScopeManager
    -0.53
    Cyfeiriadau
    -0.44
    prudence
    -0.43
     Савезне
    -0.43
    ocratic
    -0.42
    phalt
    -0.42
    正義
    -0.40
     trem
    -0.40
    Dav
    -0.40
    POSITIVE LOGITS
     Chamber
    0.80
    Chamber
    0.74
     chamber
    0.73
     CHAMBER
    0.72
    chamber
    0.69
    wan
    0.62
     spare
    0.61
     commodity
    0.57
     thể
    0.56
    Clik
    0.56
    Activations Density 0.663%

    No Known Activations