© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 780
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1407
    +0.11
    0.4%
    1023
    +0.09
    0.3%
    1810
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.11
    0.03
    1335
    +0.09
    0.02
    1768
    +0.09
    0.02
    Negative Logits
    <bos>
    -1.11
    ⓧ
    -0.69
     също
    -0.67
    േ
    -0.66
     сім
    -0.66
    public
    -0.65
     тук
    -0.64
    <tbody>
    -0.64
    void
    -0.63
     settle
    -0.63
    POSITIVE LOGITS
     Jonathan
    2.22
    Jonathan
    2.03
     maneu
    1.85
     emphat
    1.84
     shenan
    1.80
     accla
    1.79
     depic
    1.78
     strick
    1.77
     increa
    1.72
     affor
    1.71
    Activations Density 0.116%

    No Known Activations