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. 102621
    Prev
    Next
    INDEX
    Explanations

    references to underlying concepts or mechanisms in various contexts

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

    underlying structures and concepts

    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
     useAppContext
    -0.75
    majánló
    -0.68
    évaluateur
    -0.64
    SBATCH
    -0.63
    contentLoaded
    -0.60
     հղումներ
    -0.59
     ainfi
    -0.58
    parsedMessage
    -0.57
     Anſ
    -0.57
    arangay
    -0.56
    POSITIVE LOGITS
     underlying
    2.19
    underlying
    1.98
     Underlying
    1.93
    Underlying
    1.86
     underlie
    1.27
     underlies
    1.23
     underpin
    0.95
     underneath
    0.94
     beneath
    0.85
    Beneath
    0.82
    Activations Density 0.008%

    No Known Activations