© 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. 1498
    Prev
    Next
    INDEX
    Explanations

    orchestral terms, music competitions, and notable orchestras

    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
    1677
    +0.09
    0.2%
    1437
    +0.08
    0.2%
    950
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.09
    0.01
    1363
    +0.08
    0.03
    690
    +0.07
    0.03
    Negative Logits
     Glou
    -0.81
     McInt
    -0.79
     forbear
    -0.77
     Eft
    -0.77
     Daven
    -0.72
     Vaugh
    -0.71
     cabrio
    -0.67
     casio
    -0.64
     Kruse
    -0.63
     kollek
    -0.63
    POSITIVE LOGITS
     Symphony
    2.19
    Symphony
    1.56
     symphony
    1.39
     Symphon
    1.08
     symphon
    0.99
     sympy
    0.74
     psycopg
    0.72
     zipfile
    0.72
     pylab
    0.71
     Concerto
    0.70
    Activations Density 0.257%

    No Known Activations