© 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. 33-GEMMASCOPE-RES-16K
    11. 11142
    Prev
    Next
    INDEX
    Explanations

    occurrences of hyphens and dashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     „
    -0.60
     ‚
    -0.46
    „
    -0.45
    ՚
    -0.44
     („
    -0.43
    ollection
    -0.41
    ⇑
    -0.40
    }">
    -0.40
    ")]
    -0.40
    ์
    -0.38
    POSITIVE LOGITS
    //--
    0.90
    :--
    0.85
    (--
    0.81
    #--
    0.80
     --
    0.80
    !--
    0.78
    |--
    0.77
    ,--
    0.77
    .--
    0.76
    "--
    0.76
    Activations Density 0.471%

    No Known Activations