© 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. 0-GEMMASCOPE-RES-16K
    11. 10089
    Prev
    Next
    INDEX
    Explanations

    terms related to privacy and secrecy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.41
    Попис
    -0.40
    BufferException
    -0.40
    impresa
    -0.38
     JpaRepository
    -0.38
     Públicas
    -0.37
    RICT
    -0.37
     dirait
    -0.37
    stellungs
    -0.37
     GenerationType
    -0.36
    POSITIVE LOGITS
     undisclosed
    0.77
     anonymous
    0.73
     privately
    0.73
     obscure
    0.67
     secretive
    0.66
     confidential
    0.64
     mysterious
    0.63
     Anonymous
    0.63
     enigmatic
    0.62
    setContentView
    0.61
    Activations Density 2.038%

    No Known Activations