© 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. 11208
    Prev
    Next
    INDEX
    Explanations

    references to the term "Hash" and its variations in connection with specific cultural or historical contexts

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

    Starts with "Ash" or "Hash"

    np_acts-logits-general · gemini-2.0-flash

    Ash and Hash words

    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
    bootstrapcdn
    -0.74
     AspNetCore
    -0.68
     AttributeSet
    -0.67
    complexContent
    -0.66
    MergeFrom
    -0.64
    ed
    -0.63
    出版年
    -0.62
    醐
    -0.60
    ➟
    -0.60
     initComponents
    -0.60
    POSITIVE LOGITS
    hhhhhhhh
    0.64
    hhhh
    0.60
    HHHH
    0.59
     Tash
    0.58
    hhh
    0.57
    hhhhh
    0.54
    hh
    0.54
    kesan
    0.53
    HHH
    0.53
    s
    0.53
    Activations Density 0.128%

    No Known Activations