© 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. 3-GEMMASCOPE-RES-16K
    11. 9876
    Prev
    Next
    INDEX
    Explanations

    references to numerical identifiers or placeholders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bourgoin
    -0.56
    AppMethodBeat
    -0.56
    Commentaires
    -0.54
     Glossary
    -0.54
    Dettagli
    -0.54
    FileDialog
    -0.53
    ('-'
    -0.52
    pantalones
    -0.51
     Leif
    -0.49
     KT
    -0.49
    POSITIVE LOGITS
     -->
    2.39
    -->
    1.77
     -->
    1.72
     --->
    1.12
    --->
    1.10
    ]-->
    1.09
    -->
    1.05
    –>
    0.97
     →
    0.93
    ---->
    0.92
    Activations Density 0.058%

    No Known Activations