© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    language indicating rules, guidelines, or procedures

    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
    1678
    +0.10
    0.3%
    1492
    +0.09
    0.3%
    1757
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1690
    +0.10
    0.02
    792
    +0.09
    0.02
    204
    +0.08
    0.01
    Negative Logits
    hoeddwyd
    -0.69
    AddWithValue
    -0.69
    cout
    -0.64
    Já
    -0.64
    printf
    -0.64
    迫
    -0.64
    mrow
    -0.64
    ാ
    -0.63
    息
    -0.63
     điện
    -0.62
    POSITIVE LOGITS
     maneu
    2.17
     undertakes
    2.12
     undertake
    2.12
     impra
    2.11
     suscep
    2.10
     undertaking
    2.10
     increa
    2.09
     guarante
    2.09
     shenan
    2.08
     undertook
    2.06
    Activations Density 0.258%

    No Known Activations