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. 8855
    Prev
    Next
    INDEX
    Explanations

    terms related to product features and customer concerns in a sales context

    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
     nakalista
    -0.76
    AccessorTable
    -0.71
     חיצוניים
    -0.67
    ंदीखरीदारी
    -0.67
    LookAnd
    -0.64
     ModelExpression
    -0.62
    EndProject
    -0.62
    angliski
    -0.62
    pexpr
    -0.61
    HomeAsUpEnabled
    -0.60
    POSITIVE LOGITS
     altrett
    0.46
     capital
    0.46
    capital
    0.44
    RuntimeObject
    0.43
     άν
    0.42
     Verhältnis
    0.42
     reckoned
    0.41
     Dau
    0.41
    ConstraintMaker
    0.40
    gypti
    0.39
    Activations Density 0.126%

    No Known Activations