© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11242
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to preferences and referrals

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

    "prefer" or "procedure"

    np_acts-logits-general · gemini-2.0-flash

    prefer to / preferred than / procedure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Opti
    -0.66
     Moos
    -0.63
    Mich
    -0.63
    Ghost
    -0.61
    onOptions
    -0.59
    PS
    -0.59
     conso
    -0.59
    itson
    -0.58
     Michal
    -0.58
     DPS
    -0.58
    POSITIVE LOGITS
     mitään
    0.61
     efectuar
    0.49
     auftreten
    0.49
    期刊论文
    0.48
    detectChanges
    0.48
     Shall
    0.46
     avviene
    0.46
     furono
    0.46
     dotyczą
    0.46
     refirió
    0.45
    Activations Density 0.258%

    No Known Activations