© 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. 1416
    Prev
    Next
    INDEX
    Explanations

    the name "Zach" occurring in the text

    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
    492
    +0.12
    0.4%
    1047
    +0.11
    0.4%
    316
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.04
    517
    +0.11
    0.03
    1047
    +0.10
    0.02
    Negative Logits
    zają
    -0.79
    <bos>
    -0.77
    zący
    -0.74
    ząca
    -0.74
     establish
    -0.70
    void
    -0.70
    ровала
    -0.70
    zonego
    -0.69
    ząc
    -0.69
     express
    -0.69
    POSITIVE LOGITS
     effe
    2.18
     dispen
    1.99
     nece
    1.99
     increa
    1.96
     unden
    1.94
     embra
    1.94
     affor
    1.91
     inev
    1.89
     illi
    1.88
     accla
    1.87
    Activations Density 0.132%

    No Known Activations