© 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. 31-GEMMASCOPE-RES-16K
    11. 9744
    Prev
    Next
    INDEX
    Explanations

    code related to function definitions and status retrievals within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    PHP code syntax and object-oriented programming patterns involving method calls and class structures.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.34
    bosky
    -0.34
    Referencie
    -0.34
    ProgressHUD
    -0.33
     Carolina
    -0.32
    دانشنامهٔ
    -0.32
     Walla
    -0.31
    nads
    -0.30
     Venezuelan
    -0.30
     IUser
    -0.29
    POSITIVE LOGITS
     Magento
    0.71
    Magento
    0.68
     Mage
    0.56
    fjspx
    0.56
    principalColumn
    0.54
    XmlAccessorType
    0.52
    parsedMessage
    0.52
     Maharashtra
    0.52
    Mage
    0.51
     mage
    0.49
    Activations Density 0.151%

    No Known Activations