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. 1-GEMMASCOPE-RES-16K
    6. 7012
    Prev
    Next
    INDEX
    Explanations

    references to salt and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    例文帳に追加
    -0.57
     Incompatible
    -0.57
     continúas
    -0.56
    beiro
    -0.54
    stdc
    -0.54
    DialogInterface
    -0.53
    itemBuilder
    -0.53
    osoma
    -0.53
    shub
    -0.52
     accounting
    -0.52
    POSITIVE LOGITS
     salt
    1.80
    salt
    1.68
     Salt
    1.50
    Salt
    1.49
     SALT
    1.44
    SALT
    1.17
     salts
    1.14
     Salts
    1.04
     rely
    0.97
    盐
    0.89
    Activations Density 0.080%

    No Known Activations