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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5820
    Prev
    Next
    INDEX
    Explanations

    words related to entomology and specific entomological terms

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

    Followed by non-English words

    np_acts-logits-general · gemini-2.0-flash

    sequences often from different languages

    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
     صوتيه
    -0.59
    Biographie
    -0.54
    uszki
    -0.52
    entendre
    -0.51
     Jugendliche
    -0.50
    neté
    -0.50
    تقاوى
    -0.49
     bfs
    -0.48
    basics
    -0.48
     PDR
    -0.47
    POSITIVE LOGITS
    Diwedd
    0.58
    ciech
    0.55
    σεων
    0.54
    monių
    0.53
    ftagPool
    0.52
    nych
    0.52
    inkl
    0.52
    arraycopy
    0.52
     Recognition
    0.51
    politan
    0.51
    Activations Density 0.026%

    No Known Activations