© 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. 6-RES-JB
    11. 7933
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    1343
    +0.17
    0.7%
    50
    +0.14
    0.5%
    1177
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.17
    0.11
    227
    +0.14
    0.09
    678
    +0.11
    0.09
    Negative Logits
    <bos>
    -1.80
     jakarta
    -0.86
     intersper
    -0.85
    ⓧ
    -0.77
    qiao
    -0.77
    harmed
    -0.77
     endeavouring
    -0.76
    xiu
    -0.76
     Molière
    -0.74
     elena
    -0.74
    POSITIVE LOGITS
     Manufact
    0.84
     Underwear
    0.75
     Ename
    0.73
     Ornaments
    0.70
    Xoxo
    0.69
    BEAUT
    0.69
     Adhe
    0.68
    Sooo
    0.67
    AWESOME
    0.66
    isDebug
    0.65
    Activations Density 0.512%

    No Known Activations