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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6584
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and their properties, particularly in construction and engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SourceChecksum
    -0.65
    RTEE
    -0.62
    adaptiveStyles
    -0.59
    ngdoc
    -0.59
     AssemblyCulture
    -0.56
    WebVitals
    -0.55
    ftagPool
    -0.54
    SequentialGroup
    -0.52
    cticut
    -0.52
    contentLoaded
    -0.52
    POSITIVE LOGITS
    jooq
    0.32
    Transkript
    0.32
    rašymas
    0.31
     Valent
    0.29
     habitación
    0.28
     maintien
    0.28
    greSQL
    0.28
     sugg
    0.27
     TMPro
    0.26
    farwyddwr
    0.26
    Activations Density 0.348%

    No Known Activations