Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1195
    Prev
    Next
    INDEX
    Explanations

    terms related to supplementary roles or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    0.6%
    1092
    +0.10
    0.3%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.17
    0.03
    474
    +0.10
    0.02
    1363
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.34
    ⓧ
    -0.87
    <?
    -0.86
    AllowUser
    -0.74
    /**
    -0.72
    bardziej
    -0.71
    CreateMap
    -0.71
     Administrativna
    -0.69
    Fordítás
    -0.68
    脚注の使い方
    -0.67
    POSITIVE LOGITS
     aen
    1.85
     secon
    1.74
     disagre
    1.73
     fta
    1.73
     thut
    1.72
     fte
    1.67
     maneu
    1.64
     wien
    1.63
     squa
    1.62
     foon
    1.62
    Activations Density 0.297%

    No Known Activations