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. 0-GEMMASCOPE-MLP-16K
    6. 59
    Prev
    Next
    INDEX
    Explanations

    themes related to daily practices and routines

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

    references to daily practices and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walkover
    -0.90
     виправивши
    -0.85
    NameInMap
    -0.83
    __":
    
    -0.82
    #+#
    -0.78
    Personensuche
    -0.73
    Kariera
    -0.73
     متعلقه
    -0.72
    MigrationBuilder
    -0.72
    DockStyle
    -0.71
    POSITIVE LOGITS
    abi
    0.48
    hintText
    0.46
     Grö
    0.44
    ModelMap
    0.44
     skolen
    0.44
     RIAA
    0.43
     settled
    0.43
     Roe
    0.42
     Rosetta
    0.41
     Olds
    0.41
    Activations Density 0.976%

    No Known Activations