© 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. 3380
    Prev
    Next
    INDEX
    Explanations

    references to ranges, particularly in scientific or technical contexts

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

    numerical ranges with values and units.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    numerical ranges and intervals specified with numbers and units.

    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
    RTEX
    -0.56
    évaluateur
    -0.50
    WaitGroup
    -0.47
    principalColumn
    -0.44
     Савезне
    -0.44
     ComVisible
    -0.43
    enschappelijke
    -0.43
     thiệu
    -0.42
    Personensuche
    -0.42
    EndGlobalSection
    -0.42
    POSITIVE LOGITS
     range
    2.81
     ranges
    2.45
     Range
    2.33
    range
    2.31
    Range
    2.20
     RANGE
    2.19
     Ranges
    2.05
    RANGE
    1.95
    ranges
    1.94
     диапа
    1.88
    Activations Density 1.383%

    No Known Activations