© 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. 31-GEMMASCOPE-RES-16K
    11. 3439
    Prev
    Next
    INDEX
    Explanations

    requests or suggestions related to "making" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    imperative instructions or directives using "make sure" constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.59
    LookAnd
    -0.53
    middels
    -0.52
    bootstrapcdn
    -0.51
     Grüsse
    -0.50
    Tikang
    -0.49
    AppMethodBeat
    -0.48
    agisse
    -0.48
     AssemblyTitle
    -0.47
    medriver
    -0.47
    POSITIVE LOGITS
     sure
    1.95
    sure
    1.27
    Sure
    1.20
     Sure
    1.19
     SURE
    1.13
     ensure
    0.90
     certeza
    0.86
    ensure
    0.73
     sicher
    0.71
     assure
    0.70
    Activations Density 0.096%

    No Known Activations