© 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. 1528
    Prev
    Next
    INDEX
    Explanations

    references to historical events or 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
    90
    +0.11
    0.4%
    1742
    +0.07
    0.2%
    241
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.05
    1120
    +0.07
    0.05
    690
    +0.07
    0.04
    Negative Logits
    <bos>
    -0.84
    cần
    -0.69
     robić
    -0.66
     introduce
    -0.65
     raise
    -0.64
     shuddered
    -0.63
     pull
    -0.61
     become
    -0.61
    một
    -0.61
     złoty
    -0.61
    POSITIVE LOGITS
     maneu
    1.50
     Juf
    1.48
     hcm
    1.46
     habile
    1.45
     KOR
    1.43
     unden
    1.35
     dispen
    1.35
     aen
    1.35
     quoique
    1.34
     Bulgar
    1.33
    Activations Density 0.298%

    No Known Activations