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. 1-GEMMASCOPE-MLP-16K
    6. 8798
    Prev
    Next
    INDEX
    Explanations

    phrases associated with benefits and optimization strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    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
    DebuggerStep
    -0.68
    ríamos
    -0.58
    tieth
    -0.55
    MethodManager
    -0.55
    úrate
    -0.54
     ());
    -0.54
    "]];
    -0.54
    ^(@)
    -0.54
    mistak
    -0.53
    baugh
    -0.53
    POSITIVE LOGITS
    sizeCache
    0.62
    Produzione
    0.62
    ⓘ
    0.59
    ioen
    0.59
    findpost
    0.56
    FunctionFlags
    0.52
    WebElementEntity
    0.52
     selve
    0.51
    ctivos
    0.50
    évaluateur
    0.50
    Activations Density 0.486%

    No Known Activations