© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3629
    Prev
    Next
    INDEX
    Explanations

    references to liquid substances, particularly in scientific and technical contexts

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

    "liquid" followed by specific nouns

    np_acts-logits-general · gemini-2.0-flash

    liquid + scientific/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interesse
    -0.57
    MessageOf
    -0.56
    TextHelper
    -0.51
     îns
    -0.51
     echi
    -0.49
     sla
    -0.47
     asthma
    -0.47
     tachycardia
    -0.46
    __[
    -0.46
    AddField
    -0.46
    POSITIVE LOGITS
    tagext
    0.75
    Filmografie
    0.74
     '\\;'
    0.74
    DockStyle
    0.72
     phase
    0.70
    ambar
    0.70
    ificador
    0.68
    DOCTYPE
    0.67
    Parcelize
    0.65
    脚注の使い方
    0.65
    Activations Density 0.206%

    No Known Activations