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. 1
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to quantum physics and authentication systems

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

    signs and factors related to authentication systems

    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
    odb
    -0.63
    Viited
    -0.59
    godic
    -0.58
    StoryboardSegue
    -0.57
    LookAnd
    -0.57
    obox
    -0.57
     viera
    -0.57
     ammon
    -0.55
    ruik
    -0.54
    脚注
    -0.54
    POSITIVE LOGITS
    LayoutStyle
    0.65
     @"/
    0.63
    enumi
    0.52
     CURIAM
    0.51
    PageModule
    0.49
    sidemargin
    0.49
    ]--;
    0.48
    tifying
    0.46
    </tfoot>
    0.44
    usercontent
    0.44
    Activations Density 0.584%

    No Known Activations