© 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-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6415
    Prev
    Next
    INDEX
    Explanations

    references to following actions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.61
     initComponents
    -0.59
    dataclass
    -0.52
    nically
    -0.51
    wußt
    -0.49
    MigrationBuilder
    -0.49
    quinas
    -0.49
    Personendaten
    -0.49
    ChildScrollView
    -0.49
    IContainer
    -0.48
    POSITIVE LOGITS
    Follow
    1.18
     Follow
    1.15
     follow
    1.12
     FOLLOW
    1.08
    follow
    1.05
     Follows
    1.00
     follows
    0.98
    FOLLOW
    0.97
    ofollow
    0.90
     Followed
    0.89
    Activations Density 0.172%

    No Known Activations