© 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. 31-GEMMASCOPE-RES-16K
    6. 498
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and types in programming

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

    function and method declarations in C++ 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
     endforeach
    -0.37
    Revenir
    -0.36
     Töchter
    -0.35
     Dostupné
    -0.34
    JsonInclude
    -0.33
    AppMethodBeat
    -0.32
     faits
    -0.32
     يتيمه
    -0.32
    expandindo
    -0.32
     இரு
    -0.32
    POSITIVE LOGITS
     operator
    0.66
     operators
    0.57
    operator
    0.56
    EFIAPI
    0.54
     Operators
    0.52
    Портали
    0.51
    Operators
    0.51
    balleur
    0.50
     Operator
    0.49
    __":
    0.49
    Activations Density 0.215%

    No Known Activations