© 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. 998
    Prev
    Next
    INDEX
    Explanations

    titles or phrases indicating a narrative or story

    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
    1937
    +0.26
    1.4%
    1573
    +0.18
    1.0%
    1472
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.26
    0.06
    1573
    +0.18
    0.04
    1872
    +0.17
    0.05
    Negative Logits
    <bos>
    -1.15
     كومونز
    -0.85
    expandindo
    -0.76
    WriteLiteral
    -0.73
    GIH
    -0.72
    ations
    -0.72
    UMBUS
    -0.71
    ISMS
    -0.71
    ostruct
    -0.70
    InputBorder
    -0.70
    POSITIVE LOGITS
     affor
    2.15
     increa
    2.08
     maneu
    2.01
     impra
    2.00
     sergio
    1.97
     hairc
    1.95
     reluct
    1.95
     ecru
    1.94
     inconce
    1.91
     indestru
    1.88
    Activations Density 0.550%

    No Known Activations