© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6672
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "form" and related derivations used in different contexts

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

    following "Form" or "form"

    np_acts-logits-general · gemini-2.0-flash

    form followed by ative, ally, or ula

    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
     متعلقه
    -0.58
     fiscales
    -0.56
    ########.
    -0.55
    tamento
    -0.54
     Offisielt
    -0.54
     Visconti
    -0.54
    AndFlush
    -0.53
     Fische
    -0.53
    wyczaj
    -0.52
    pædia
    -0.52
    POSITIVE LOGITS
    idable
    0.94
    ulates
    0.80
    ulir
    0.79
    alised
    0.74
    bootstrapcdn
    0.72
    ulated
    0.71
    ulate
    0.69
    ulators
    0.65
    ulating
    0.65
    Factor
    0.62
    Activations Density 0.214%

    No Known Activations