© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 69585
    Prev
    Next
    INDEX
    Explanations

    references to flexible materials and their applications

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

    flexible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    fördert
    -0.44
     JpaRepository
    -0.43
    OGND
    -0.40
    SequentialGroup
    -0.39
    ContentLoaded
    -0.38
    providedIn
    -0.37
    requireNonNull
    -0.36
     CreateTagHelper
    -0.36
    èdia
    -0.36
    exitRule
    -0.35
    POSITIVE LOGITS
     flexible
    1.69
     flexibility
    1.60
     Flexibility
    1.55
     Flexible
    1.52
    Flexibility
    1.49
    Flexible
    1.47
    flexible
    1.45
     flexibles
    1.44
     flexib
    1.43
     flexível
    1.41
    Activations Density 0.155%

    No Known Activations