© 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. 25-GEMMASCOPE-RES-16K
    11. 1525
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey a sense of danger or negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GIVEREF
    -0.73
    日閲覧
    -0.58
    RefNanny
    -0.58
    __':
    -0.57
    setcounter
    -0.56
    enterOuterAlt
    -0.56
    addPreferredGap
    -0.55
     muhimu
    -0.54
    Biblia
    -0.54
    djangoproject
    -0.52
    POSITIVE LOGITS
     sounding
    0.79
    erweise
    0.76
    sounding
    0.71
    ly
    0.69
     situations
    0.69
    ness
    0.65
     looking
    0.65
    looking
    0.64
     behavior
    0.63
     behaviour
    0.62
    Activations Density 0.458%

    No Known Activations