© 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. 3413
    Prev
    Next
    INDEX
    Explanations

    code structure and elements related to client interactions and responses

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

    object-oriented class and method definitions in programming code.

    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
    !("{
    -0.35
    ']));
    -0.30
    ()',
    -0.29
    ?
    -0.29
    ()))
    -0.29
     Begle
    -0.28
    ())))
    -0.27
    ())),
    -0.27
     Transparen
    -0.27
     støtte
    -0.27
    POSITIVE LOGITS
    EDEFAULT
    0.76
    󠁴
    0.66
    NameInMap
    0.66
    
    0.63
     OFDb
    0.60
    astify
    0.59
    Personensuche
    0.59
     &___
    0.58
    principalTable
    0.57
     noDo
    0.57
    Activations Density 0.226%

    No Known Activations