© 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. 16135
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to software and development

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

    technical code, configuration files, and programming syntax.

    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
     مشين
    -0.45
    farwyddwr
    -0.39
     razonable
    -0.37
     ujednoznacz
    -0.36
     Exactos
    -0.36
     snippetHide
    -0.36
     spectateurs
    -0.36
     kolik
    -0.36
     lección
    -0.35
     senhora
    -0.35
    POSITIVE LOGITS
     firmware
    0.92
     flashed
    0.85
     Firmware
    0.79
     flashing
    0.78
     boot
    0.77
     ROM
    0.77
     bootloader
    0.75
     Boot
    0.73
    boot
    0.71
    firmware
    0.69
    Activations Density 0.364%

    No Known Activations