© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1470
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistical or data analysis contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.60
    </td>
    -0.59
    </s>
    -0.53
    </th>
    -0.50
    AccessorTable
    -0.46
    ")]
    
    -0.45
    tagHelperRunner
    -0.45
    SourceChecksum
    -0.44
    </h2>
    -0.42
    mybatisplus
    -0.42
    POSITIVE LOGITS
    ).
    2.23
    ".
    1.97
    }.
    1.96
    ].
    1.95
    ».
    1.91
    ”.
    1.89
    ").
    1.87
     }.
    1.83
     ».
    1.81
    ').
    1.80
    Activations Density 4.462%

    No Known Activations