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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2024
    Prev
    Next
    INDEX
    Explanations

    historical or biographical information about individuals

    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
    +0.13
    0.5%
    900
    +0.08
    0.3%
    2030
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    900
    +0.13
    0.03
    203
    +0.08
    0.03
    2030
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.49
    ⓧ
    -1.14
    
    -0.82
    <?
    -0.80
    /*
    -0.64
     colspan
    -0.64
     decide
    -0.62
     participate
    -0.61
    /**
    -0.60
    public
    -0.59
    POSITIVE LOGITS
     b
    1.74
    b
    1.38
     unden
    1.34
     maneu
    1.30
     Khart
    1.30
     increa
    1.30
     affor
    1.29
     véhic
    1.25
     quoique
    1.22
     quelquefois
    1.22
    Activations Density 0.109%

    No Known Activations