© 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 - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 3370
    Prev
    Next
    INDEX
    Explanations

    code structures and variable declarations related to array and matrix handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.35
     democrática
    -0.34
     Stuart
    -0.34
     rechazo
    -0.33
     Verantwortung
    -0.32
     parkir
    -0.32
     CORP
    -0.31
    هما
    -0.31
     Fakult
    -0.31
    彿
    -0.30
    POSITIVE LOGITS
    RegressionTest
    0.74
     autorytatywna
    0.61
    \{\\
    0.60
    PropertyChanging
    0.58
    parsedMessage
    0.57
     насељу
    0.55
    ">//
    0.54
     disambiguazione
    0.53
    ]")]
    0.53
    ParallelGroup
    0.53
    Activations Density 0.419%

    No Known Activations