© 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. 214
    Prev
    Next
    INDEX
    Explanations

    lengthy descriptions and stories with a professional or formal tone

    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
    266
    +0.08
    0.3%
    1233
    +0.07
    0.3%
    1612
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1612
    +0.08
    0.03
    266
    +0.07
    0.02
    1233
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.86
    public
    -0.65
    //
    -0.63
    <?
    -0.63
     regulate
    -0.62
    /***
    -0.62
    
    -0.61
     can
    -0.61
     also
    -0.59
     port
    -0.59
    POSITIVE LOGITS
     meaningful
    2.30
     meaningfully
    1.74
     fatis
    1.72
     maroc
    1.62
     tramont
    1.55
     mosso
    1.54
     ibiza
    1.53
     stockholm
    1.51
     imposs
    1.51
     casio
    1.50
    Activations Density 0.119%

    No Known Activations