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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 22-GEMMASCOPE-MLP-16K
    6. 15796
    Prev
    Next
    INDEX
    Explanations

    elements related to fishing and marine activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    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
     drop
    -0.46
    nop
    -0.45
    tura
    -0.44
     NP
    -0.44
    ś
    -0.42
    ax
    -0.41
    cover
    -0.41
     bailey
    -0.41
    шься
    -0.41
    princ
    -0.41
    POSITIVE LOGITS
    findpost
    0.81
    Obrázky
    0.81
    ⓧ
    0.71
     ModelExpression
    0.68
    TagMode
    0.68
    MLLoader
    0.67
    ')")
    0.67
    Tikang
    0.64
     متعلقه
    0.62
    AndEndTag
    0.61
    Activations Density 0.078%

    No Known Activations