© 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. 1-GEMMASCOPE-RES-16K
    11. 8131
    Prev
    Next
    INDEX
    Explanations

    terms related to "compilation" and "restriction."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.47
    :"-"`
    -0.46
     heridos
    -0.44
     transparence
    -0.43
    EndGlobalSection
    -0.43
     Comer
    -0.43
    ędziesz
    -0.43
     alza
    -0.42
     tää
    -0.41
     Neubau
    -0.41
    POSITIVE LOGITS
     Comp
    1.09
    comp
    1.06
     comp
    1.05
     COMP
    0.93
    Comp
    0.90
    COMP
    0.88
     Bind
    0.83
     constraint
    0.82
     bind
    0.80
     BIND
    0.79
    Activations Density 0.351%

    No Known Activations