© 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. 9546
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, particularly related to class and method definitions

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

    Java stack traces and error logs from software exceptions.

    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
     kasarigan
    -0.72
     CreateTagHelper
    -0.72
    ChildScrollView
    -0.70
    ftagPool
    -0.69
    httphttps
    -0.66
    complexContent
    -0.65
     Infórmanos
    -0.65
     transfieras
    -0.62
    Jîn
    -0.61
    styleType
    -0.59
    POSITIVE LOGITS
     konkret
    0.33
     inneren
    0.32
    éron
    0.31
     demostrar
    0.31
     specifico
    0.29
     leeftijd
    0.29
     Inner
    0.29
     sebaliknya
    0.28
     Demonstrate
    0.28
     Live
    0.28
    Activations Density 0.529%

    No Known Activations