© 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. 437
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    0.8%
    131
    +0.04
    0.2%
    1404
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1003
    +0.14
    0.09
    956
    +0.04
    0.09
    131
    +0.04
    0.08
    Negative Logits
    <bos>
    -1.48
    ⓧ
    -1.09
    
    -0.98
    <?
    -0.97
    /**
    -0.94
    /*
    -0.83
     stabilize
    -0.75
     strengthen
    -0.75
     regain
    -0.74
     prepare
    -0.73
    POSITIVE LOGITS
     Juf
    1.64
     wien
    1.63
     embodi
    1.62
     applau
    1.62
     lele
    1.57
     maroc
    1.57
     aen
    1.57
     maneu
    1.56
     squa
    1.55
     affor
    1.55
    Activations Density 0.354%

    No Known Activations