© 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. 8964
    Prev
    Next
    INDEX
    Explanations

    subjective commentary on entertainment quality

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

    This neuron detects words and phrases that express criticism or negative evaluation of a work's flaws while acknowledging its strengths.

    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
    reactstrap
    -0.44
    ValueStyle
    -0.42
    ParallelGroup
    -0.41
    Theore
    -0.39
    principalTable
    -0.39
     Theore
    -0.37
     оригіналу
    -0.36
    IVEREF
    -0.36
     GenerationType
    -0.34
    liceerd
    -0.34
    POSITIVE LOGITS
     cliche
    0.86
     contrived
    0.85
     clich
    0.82
     cliché
    0.80
     cheesy
    0.79
     clichés
    0.77
     clic
    0.76
     tacky
    0.75
     overly
    0.74
     gimmick
    0.72
    Activations Density 0.389%

    No Known Activations