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. 36-GEMMASCOPE-RES-16K
    6. 11666
    Prev
    Next
    INDEX
    Explanations

    terms indicating invitations and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.47
    PostExecute
    -0.43
     bezig
    -0.40
    phazard
    -0.35
    MessageTagHelper
    -0.35
    选手
    -0.35
    锈钢
    -0.35
    vège
    -0.33
    MigrationBuilder
    -0.33
    Aholisi
    -0.33
    POSITIVE LOGITS
     invitation
    2.91
     invite
    2.81
     invitations
    2.63
     invites
    2.55
     invited
    2.53
     Invite
    2.48
    invitation
    2.44
    invite
    2.42
     Invitation
    2.42
     INV
    2.38
    Activations Density 0.413%

    No Known Activations