© 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. 22-GEMMASCOPE-RES-16K
    6. 10146
    Prev
    Next
    INDEX
    Explanations

    subjective evaluations or personal experiences related to feelings and impressions

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

    Followed by a form of "have."

    np_acts-logits-general · gemini-2.0-flash

    has

    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
    原始内容存档于
    -0.60
    Odpo
    -0.55
    ilarang
    -0.52
    Brainz
    -0.52
    luke
    -0.52
    modity
    -0.50
    raltar
    -0.49
     remercie
    -0.49
    reuse
    -0.49
     orienti
    -0.49
    POSITIVE LOGITS
    tvguidetime
    0.66
    awtextra
    0.61
     تضيفلها
    0.60
    KURZBESCHREIBUNG
    0.57
    GraphicsUnit
    0.56
    HasAnnotation
    0.54
    
    0.53
     ModelExpression
    0.53
    الدراسه
    0.52
     imparts
    0.51
    Activations Density 0.200%

    No Known Activations