© 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. 783
    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
    421
    +0.12
    0.4%
    645
    +0.12
    0.4%
    667
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.12
    0.03
    645
    +0.12
    0.03
    1343
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.66
    ,
    -0.64
     en
    -0.64
    .
    -0.62
    埔
    -0.62
    <eos>
    -0.61
            
    -0.61
    ה
    -0.61
     мед
    -0.60
    /**
    -0.60
    POSITIVE LOGITS
     Sar
    2.83
    Sar
    2.65
     sar
    2.35
    sar
    2.06
     SAR
    1.78
     affor
    1.66
    SAR
    1.66
     sara
    1.64
     emphat
    1.61
     impra
    1.60
    Activations Density 0.213%

    No Known Activations