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. 15812
    Prev
    Next
    INDEX
    Explanations

    technical terms related to soil treatment and waste management processes

    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
    COUVER
    -0.71
    ipedi
    -0.65
    NUMX
    -0.61
     محفوظة
    -0.60
    География
    -0.54
    GraphicsUnit
    -0.54
    ragan
    -0.53
    wurf
    -0.53
    heritance
    -0.52
    ArrowToggle
    -0.52
    POSITIVE LOGITS
    tif
    0.54
    .*")]
    0.54
    ########.
    0.52
    cookieParser
    0.52
    principalTable
    0.48
    tonode
    0.46
    RPD
    0.45
    ChildScrollView
    0.45
     Bacchus
    0.45
     العد
    0.44
    Activations Density 0.205%

    No Known Activations