© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 601
    Prev
    Next
    INDEX
    Explanations

    references to clothing items or materials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1921
    +0.11
    0.4%
    871
    +0.09
    0.3%
    1520
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.11
    0.03
    773
    +0.09
    0.02
    871
    +0.07
    0.02
    Negative Logits
    ///**
    -0.66
     /**
    -0.56
    <!--
    -0.55
     disbur
    -0.53
    <bos>
    -0.52
     reinstate
    -0.51
    //---
    -0.51
    /**
    -0.50
     rehabilitate
    -0.50
     neutralize
    -0.49
    POSITIVE LOGITS
     crop
    2.69
     Crop
    2.41
     crops
    2.38
    crop
    2.24
    Crop
    2.21
     Crops
    2.15
     cropping
    1.90
    crops
    1.87
     cropped
    1.74
    cropped
    1.40
    Activations Density 0.172%

    No Known Activations