Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 14296
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to metrics and distances in mathematical contexts

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

    metric approximation property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.50
    ByExample
    -0.42
     thomas
    -0.40
     setEmail
    -0.40
    URERS
    -0.39
     Runnable
    -0.39
     Shakspeare
    -0.38
    ftant
    -0.38
     Administração
    -0.38
    AndEndTag
    -0.38
    POSITIVE LOGITS
    mannian
    0.57
    awtextra
    0.46
    UnitTesting
    0.45
     geodesic
    0.43
    enterOuterAlt
    0.43
     metric
    0.41
    hoeddwyd
    0.40
    RepeatedField
    0.40
    stdc
    0.40
     surla
    0.39
    Activations Density 0.385%

    No Known Activations