© 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. 1617
    Prev
    Next
    INDEX
    Explanations

    copyright symbols

    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
    50
    +0.10
    0.3%
    1671
    +0.08
    0.3%
    559
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.10
    0.04
    1577
    +0.08
    0.04
    1792
    +0.06
    0.04
    Negative Logits
    lateinit
    -0.78
    -0.74
    }{||
    -0.73
    println
    -0.72
    public
    -0.72
    mtrl
    -0.71
    -0.71
     have
    -0.71
    ModelAttribute
    -0.69
     keep
    -0.69
    POSITIVE LOGITS
     maneu
    2.49
     increa
    2.48
     affor
    2.47
     effe
    2.27
     inev
    2.26
     impra
    2.25
     suscep
    2.22
     reluct
    2.22
     wherea
    2.22
     excru
    2.21
    Activations Density 0.145%

    No Known Activations