© 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. 9010
    Prev
    Next
    INDEX
    Explanations

    descriptions of fishing experiences

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

    Preceding animal names with adjectives

    np_acts-logits-general · gemini-2.0-flash

    large piece, nice barracuda

    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
     fished
    -0.93
     fishing
    -0.89
     aquatic
    -0.87
    Fishing
    -0.87
     fisherman
    -0.86
     fishermen
    -0.85
     Fishing
    -0.85
     FISHING
    -0.84
     fisheries
    -0.83
     Fisheries
    -0.80
    POSITIVE LOGITS
     school
    0.55
     School
    0.52
    errHandler
    0.49
     Bram
    0.47
    school
    0.47
    School
    0.46
    SCHOOL
    0.44
     لينك
    0.43
     schools
    0.42
    djangoproject
    0.42
    Activations Density 0.087%

    No Known Activations