© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104570
    Prev
    Next
    INDEX
    Explanations

    specific numerical and case-related data within legal documents

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

    Words or phrases representing specific quantities, samples, or reference entities in academic, scientific, or legal documents.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.44
     informée
    -0.42
    AndEndTag
    -0.38
     spin
    -0.37
     Baillargeon
    -0.37
     subnet
    -0.37
     Möglich
    -0.37
    SourceChecksum
    -0.37
     MFA
    -0.37
    Дереккөздер
    -0.36
    POSITIVE LOGITS
     samples
    0.47
     échanti
    0.46
    TestBed
    0.44
     prototypes
    0.43
    Geplaatst
    0.43
    Samples
    0.43
     exempl
    0.43
    ChildScrollView
    0.42
     sample
    0.41
     Samples
    0.40
    Activations Density 0.292%

    No Known Activations