© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 4291
    Prev
    Next
    INDEX
    Explanations

    the presence of contrasting or conflicting opinions and experiences in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.22
     AssemblyCulture
    -1.16
    MigrationBuilder
    -1.15
    клопе
    -1.13
    EDEFAULT
    -1.05
    ftagPool
    -0.99
    存于互联网档案馆
    -0.95
     itſelf
    -0.94
    '},
    -0.94
     }}$}
    -0.91
    POSITIVE LOGITS
    .
    0.46
     bocas
    0.43
     such
    0.43
     often
    0.41
     including
    0.41
     sconto
    0.40
    telor
    0.40
     many
    0.39
     so
    0.38
    Surname
    0.38
    Activations Density 0.567%

    No Known Activations