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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 0
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Test List With Features

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.12
    0.5%
    1145
    +0.07
    0.3%
    814
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.12
    0.05
    1343
    +0.07
    0.04
    1145
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.63
     springfox
    -0.84
    ⓧ
    -0.73
     expand
    -0.70
     establish
    -0.70
    <?
    
    -0.69
     colspan
    -0.68
    
    
    -0.68
     engage
    -0.67
    /**
    -0.66
    POSITIVE LOGITS
     accla
    1.68
     véhic
    1.64
     affor
    1.63
     délib
    1.60
     effe
    1.60
    de
    1.59
     mef
    1.56
     wien
    1.56
     maneu
    1.56
     stockholm
    1.55
    Activations Density 0.124%

    No Known Activations