© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3513
    Prev
    Next
    INDEX
    Explanations

    phrases associated with deprivation and accusations

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

    Accusations or deprivations of rights

    np_acts-logits-general · gemini-2.0-flash

    depriving and accusing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.72
    unjung
    -0.55
    ิมพ์
    -0.49
    esgue
    -0.47
    nyttet
    -0.47
     Mat
    -0.47
    brenner
    -0.46
    putnik
    -0.46
    perrt
    -0.45
    dolu
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.76
     oneself
    0.69
    AccessorTable
    0.69
     оригіналу
    0.67
     فريبيس
    0.66
    ']?>
    0.65
    astify
    0.61
    ArgsConstructor
    0.61
     themſelves
    0.61
     nhau
    0.60
    Activations Density 0.221%

    No Known Activations