Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11065
    Prev
    Next
    INDEX
    Explanations

    words with specific phonetic patterns or sounds, particularly those starting with "ah" or "mah."

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

    Nonsense syllables starting with "h"

    np_acts-logits-general · gemini-2.0-flash

    syllables ending in 'ah' or 'h'

    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
    -0.66
    Джерела
    -0.63
    CurrentValue
    -0.60
    Composable
    -0.60
    windowFixed
    -0.60
     static
    -0.59
    Static
    -0.58
    able
    -0.58
    ado
    -0.55
     ब्रेकडाउन
    -0.54
    POSITIVE LOGITS
    hhh
    0.87
    hh
    0.78
    hhhh
    0.74
    hhhhh
    0.74
    hhhhhhhh
    0.72
    HHH
    0.70
    HHHH
    0.63
    HHHHHHHH
    0.59
     Cah
    0.57
     prochaines
    0.56
    Activations Density 0.151%

    No Known Activations