© 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. 568
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terminology related to health, biology, and technology

    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
    +:+
    -0.42
    драв
    -0.37
    utscher
    -0.36
    eavor
    -0.35
    Попис
    -0.35
    keyColumn
    -0.34
    detectChanges
    -0.34
    以来
    -0.34
    prisingly
    -0.34
    idios
    -0.33
    POSITIVE LOGITS
     such
    3.13
    such
    2.55
     takich
    2.16
     såsom
    2.08
     like
    1.98
    Such
    1.97
     SUCH
    1.97
     takie
    1.96
     takimi
    1.92
     seperti
    1.91
    Activations Density 2.893%

    No Known Activations