© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2804
    Prev
    Next
    INDEX
    Explanations

    information related to muscles and muscle-related health topics

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    528
    +0.09
    0.3%
    1942
    +0.09
    0.3%
    1331
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    952
    +0.09
    0.03
    1331
    +0.09
    0.03
    1942
    +0.08
    0.02
    Negative Logits
    <bos>
    -1.13
     overthrown
    -0.71
     endow
    -0.68
     endeavored
    -0.68
     unify
    -0.66
     ceded
    -0.65
     reinstate
    -0.65
     knelt
    -0.65
     abolish
    -0.65
     ratify
    -0.64
    POSITIVE LOGITS
     muscle
    2.36
     Muscle
    2.15
    muscle
    2.13
     muscles
    2.06
    Muscle
    2.01
     Muscles
    1.81
     muscular
    1.42
     riva
    1.17
     MUS
    1.17
     Messieurs
    1.16
    Activations Density 0.139%

    No Known Activations