© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13424
    Prev
    Next
    INDEX
    Explanations

    academic or legal terminology related to studies and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.47
     gyhoeddwyd
    -0.47
     bezeichneter
    -0.47
    oa̍t
    -0.47
    Viited
    -0.46
    uxxxx
    -0.46
    lapsingToolbar
    -0.42
    findpost
    -0.41
    LabelTagHelper
    -0.41
    webElementGuid
    -0.41
    POSITIVE LOGITS
     current
    3.50
     currently
    3.30
    current
    2.97
    currently
    2.92
     Currently
    2.91
     presently
    2.84
     CURRENT
    2.83
    Currently
    2.83
     Current
    2.77
    Current
    2.73
    Activations Density 2.918%

    No Known Activations