© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    concepts related to music and cultural influences

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

    comparative phrases using "so much as" or similar constructions that indicate degree or extent comparisons.

    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
     Sun
    -0.33
     Plus
    -0.32
     Cur
    -0.31
     mem
    -0.29
     detik
    -0.29
    ArgumentParser
    -0.28
    Plus
    -0.28
    ContextCompat
    -0.28
     lại
    -0.28
     Live
    -0.28
    POSITIVE LOGITS
     genauso
    1.10
     autant
    1.07
     equally
    1.02
     altrett
    1.02
     ebenso
    1.01
     enemmän
    0.99
     Equally
    0.93
     скорее
    0.90
     more
    0.85
     much
    0.84
    Activations Density 0.355%

    No Known Activations