© 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. 1156
    Prev
    Next
    INDEX
    Explanations

    references to being a part of a group, project, or initiative

    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
    355
    +0.07
    0.2%
    647
    +0.07
    0.2%
    191
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.07
    0.03
    1363
    +0.07
    0.04
    347
    +0.06
    0.03
    Negative Logits
    <bos>
    -0.79
     krishna
    -0.79
     singh
    -0.63
     Ayur
    -0.60
     kerala
    -0.55
     Punj
    -0.52
     pü
    -0.52
     ees
    -0.52
     mahar
    -0.51
     jee
    -0.50
    POSITIVE LOGITS
     applau
    1.04
     aquarelle
    0.97
     medesimo
    0.96
     Valentín
    0.95
     bourgeo
    0.94
     tricot
    0.90
     vagab
    0.87
     signore
    0.87
     Abbé
    0.86
     Shakspeare
    0.86
    Activations Density 0.683%

    No Known Activations