© 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. 6-RES-JB
    11. 5863
    Prev
    Next
    INDEX
    Explanations

    references to software applications or utilities

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    228
    +0.14
    0.7%
    406
    +0.13
    0.7%
    1296
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.09
    227
    +0.13
    0.09
    1097
    +0.13
    0.08
    Negative Logits
    <bos>
    -1.78
     vēl
    -0.89
     iesp
    -0.84
     ķ
    -0.80
     īpa
    -0.79
     šķ
    -0.79
     daudz
    -0.76
     vairāk
    -0.75
     bēr
    -0.72
     ļ
    -0.72
    POSITIVE LOGITS
     affor
    1.59
     increa
    1.56
     impra
    1.55
     milf
    1.54
     shenan
    1.49
     coar
    1.49
     madonna
    1.47
     depic
    1.47
     excru
    1.44
     lidl
    1.44
    Activations Density 0.939%

    No Known Activations