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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5183
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of social or political contexts and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.94
     للمعارف
    -0.86
     '\\;'
    -0.81
    MigrationBuilder
    -0.75
    يكب
    -0.75
    writeFieldEnd
    -0.74
    tagHelperRunner
    -0.74
     CWE
    -0.73
    IndentedString
    -0.73
    rungsseite
    -0.73
    POSITIVE LOGITS
    ↵
    0.89
    ↵↵
    0.84
    </h2>
    0.78
    </h1>
    0.67
    </b>
    0.65
     them
    0.64
    .
    0.64
    </td>
    0.63
    ")
    0.61
    ?"
    0.59
    Activations Density 7.099%

    No Known Activations