© 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. 587
    Prev
    Next
    INDEX
    Explanations

    references to "pop" or related cultural phenomena

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

    the word "Pop" in various contexts.

    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
    obium
    -0.42
    <bos>
    -0.36
    地
    -0.34
    Amount
    -0.33
     dispu
    -0.33
    官
    -0.33
    ớ
    -0.32
     Aner
    -0.31
     Fjord
    -0.31
     „
    -0.31
    POSITIVE LOGITS
     pop
    1.04
     Pop
    1.02
    Pop
    0.98
    pop
    0.92
     POP
    0.91
     pops
    0.90
     popped
    0.83
    POP
    0.83
    Pops
    0.81
     Pops
    0.81
    Activations Density 0.142%

    No Known Activations