© 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. 16050
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structure elements in code

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

    numeric values and array indices in code structures.

    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
    XmlEnum
    -0.48
    rrggbb
    -0.42
    TargetException
    -0.39
    vgili
    -0.33
    Manbalar
    -0.33
     Lastly
    -0.33
     SwitchCompat
    -0.33
     thirteenth
    -0.31
    friger
    -0.31
    grès
    -0.31
    POSITIVE LOGITS
     second
    1.29
    Second
    1.18
     secondly
    1.16
     Second
    1.16
    second
    1.16
    二
    1.11
     Secondly
    1.07
    Secondly
    1.05
     deuxième
    1.04
     SECOND
    1.03
    Activations Density 0.939%

    No Known Activations