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. 5
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and economic conditions

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

    terms related to political ideologies and economic contexts

    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
    tetlen
    -0.48
     iscri
    -0.46
    ็จ
    -0.46
    cstring
    -0.44
    temu
    -0.43
    stdc
    -0.43
     nemlig
    -0.43
    terdam
    -0.42
     haline
    -0.41
     aton
    -0.41
    POSITIVE LOGITS
    WriteTagHelper
    1.02
    setVerticalGroup
    0.83
     Administrativna
    0.82
    ंदीखरीदारी
    0.78
    mybatisplus
    0.77
    +#+#
    0.77
     getItemId
    0.75
     ModelExpression
    0.75
    numerusform
    0.75
    AddTagHelper
    0.73
    Activations Density 1.858%

    No Known Activations