© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8489
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to scientific processes and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verne
    -0.35
    ardin
    -0.35
    enseits
    -0.34
     AppCompatTheme
    -0.33
     programme
    -0.32
    ayage
    -0.32
     wider
    -0.32
     n
    -0.31
     younger
    -0.31
     consum
    -0.31
    POSITIVE LOGITS
     дописавши
    0.92
     متعلقه
    0.90
     '\\;'
    0.90
     tartalomajánló
    0.86
     surla
    0.85
    +#+#
    0.82
    ]")]
    0.80
    writeFieldEnd
    0.79
    Referanser
    0.78
    MessageOf
    0.78
    Activations Density 1.549%

    No Known Activations