© 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. 1647
    Prev
    Next
    INDEX
    Explanations

    the acronym "CST" being emphasized in the text

    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
    1438
    +0.11
    0.3%
    344
    +0.10
    0.3%
    1328
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.11
    0.07
    16
    +0.10
    0.07
    1120
    +0.10
    0.07
    Negative Logits
    <bos>
    -0.96
    Educación
    -0.82
    ・
    -0.81
    та
    -0.81
    み
    -0.80
    -0.79
      
    -0.78
    createElement
    -0.78
    カ
    -0.78
     기
    -0.78
    POSITIVE LOGITS
     affor
    3.16
     increa
    3.11
     volunte
    2.97
     inev
    2.94
     guarante
    2.92
     lidl
    2.91
     fuf
    2.87
     disagre
    2.86
     stockholm
    2.86
     reluct
    2.85
    Activations Density 0.269%

    No Known Activations