© 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. 11-GEMMASCOPE-RES-16K
    6. 5533
    Prev
    Next
    INDEX
    Explanations

    phrases indicating partial involvement or contribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    énéral
    -0.41
    bersicht
    -0.40
     TextAppearance
    -0.39
     eigentlich
    -0.39
     Naran
    -0.39
    autique
    -0.37
     anything
    -0.36
    addGap
    -0.36
    glUniform
    -0.36
     TAP
    -0.35
    POSITIVE LOGITS
     partially
    1.36
     partly
    1.29
     Partially
    1.27
     Partly
    1.20
     partial
    1.18
    Partly
    1.18
     parcialmente
    1.16
    partly
    1.16
    Partial
    1.06
     parcial
    1.06
    Activations Density 0.495%

    No Known Activations