© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 304
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations

    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
    +0.08
    0.3%
    324
    +0.06
    0.3%
    689
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.08
    0.04
    1907
    +0.06
    0.04
    306
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.12
     do
    -0.96
    </tbody>
    -0.94
    .
    -0.94
     continue
    -0.93
    ,
    -0.93
     have
    -0.91
    <eos>
    -0.91
     get
    -0.90
     in
    -0.90
    POSITIVE LOGITS
     maneu
    2.94
     increa
    2.87
     accla
    2.84
     emphat
    2.81
     affor
    2.75
     perfet
    2.72
     madonna
    2.70
     disagre
    2.68
     desir
    2.65
     inev
    2.65
    Activations Density 0.110%

    No Known Activations