© 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. 537
    Prev
    Next
    INDEX
    Explanations

    references to crafting and related activities

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

    the word "Crabtree" or words containing the substring "cra" followed by "b" or related morphemes.

    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
    httphttps
    -0.50
     linkovi
    -0.50
    complexContent
    -0.50
     kaarangay
    -0.47
    fromUtf
    -0.47
    InSection
    -0.46
     feroit
    -0.46
     avoient
    -0.46
    featureID
    -0.45
    RTDA
    -0.45
    POSITIVE LOGITS
     cra
    0.74
    Cra
    0.74
     Cra
    0.71
    cra
    0.64
     CRA
    0.58
     Cracker
    0.56
     Kra
    0.52
    CRA
    0.52
    Kra
    0.51
     kra
    0.50
    Activations Density 0.170%

    No Known Activations