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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 144
    Prev
    Next
    INDEX
    Explanations

    words related to options or alternatives

    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
    50
    +0.14
    0.6%
    1872
    +0.06
    0.2%
    1110
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1110
    +0.14
    0.05
    1243
    +0.06
    0.05
    868
    +0.05
    0.05
    Negative Logits
    <bos>
    -1.99
    public
    -0.86
    Descripció
    -0.75
    export
    -0.73
    cshtml
    -0.71
    /**
    -0.69
                
    -0.69
    void
    -0.68
    Referències
    -0.67
     continue
    -0.67
    POSITIVE LOGITS
     stockholm
    2.12
     affor
    2.10
     maneu
    2.09
     accla
    2.04
     impra
    2.02
     Juf
    1.98
     fta
    1.98
     volunte
    1.98
     increa
    1.95
     philanth
    1.94
    Activations Density 0.084%

    No Known Activations