© 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. 39-GEMMASCOPE-RES-16K
    11. 596
    Prev
    Next
    INDEX
    Explanations

    mentions of key individuals and their relationships along with associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.67
    +#+#
    -0.57
    AndEndTag
    -0.49
     invokingState
    -0.48
    AddTagHelper
    -0.46
    ValueGenerated
    -0.46
    </tfoot>
    -0.42
     MainAxisSize
    -0.42
    bootstrapcdn
    -0.42
    SuccessListener
    -0.41
    POSITIVE LOGITS
     deny
    1.55
     denies
    1.47
     denying
    1.42
     denial
    1.41
     denied
    1.40
     refute
    1.37
     refuted
    1.34
     Deny
    1.20
    deny
    1.16
    否认
    1.14
    Activations Density 0.900%

    No Known Activations