Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7303
    Prev
    Next
    INDEX
    Explanations

    concepts related to carbon management and energy changes in environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.64
    Vidite
    -0.52
    SupportActionBar
    -0.49
    principalColumn
    -0.47
    nachron
    -0.47
    Demografie
    -0.47
    ModelAdmin
    -0.46
     verwacht
    -0.44
    vician
    -0.44
     Expect
    -0.43
    POSITIVE LOGITS
     candidate
    0.43
     candidates
    0.40
    DIPSETTING
    0.38
    VersionUID
    0.38
    WireFormatLite
    0.37
     defaultstate
    0.36
    TagMode
    0.35
     klink
    0.35
     وإن
    0.35
    System
    0.34
    Activations Density 0.345%

    No Known Activations