© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics represented in the document

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

    legal case citations and numbered references formatted in official court document style.

    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
     these
    -0.58
    matchCondition
    -0.54
    these
    -0.53
     desses
    -0.52
     thefe
    -0.49
     destes
    -0.47
    These
    -0.46
     těchto
    -0.46
     estos
    -0.45
    contentLoaded
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.46
    +#+#
    0.40
     informée
    0.40
     francs
    0.36
     وتسجيلات
    0.36
    setVerticalGroup
    0.36
    ьаж
    0.35
    IBAction
    0.35
    ThroughAttribute
    0.35
     Cheddar
    0.34
    Activations Density 0.777%

    No Known Activations