Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 968
    Prev
    Next
    INDEX
    Explanations

    syntax elements and function calls in programming code

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

    function and class definitions in source 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
     başına
    -0.40
     asamblea
    -0.36
     refiere
    -0.36
     Spitze
    -0.36
     ©️
    -0.35
     deuil
    -0.35
     tepi
    -0.34
    étape
    -0.34
     actuales
    -0.33
     yerine
    -0.33
    POSITIVE LOGITS
     palindrome
    0.72
    expandindo
    0.69
     fibonacci
    0.66
     Fibonacci
    0.63
     Reverse
    0.62
     Cæsar
    0.60
     Longest
    0.60
     queſta
    0.60
    migrationBuilder
    0.59
     UserRepository
    0.59
    Activations Density 0.843%

    No Known Activations