© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    technical terms related to musical instruments and mixing equipment

    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
    893
    +0.12
    0.4%
    1937
    +0.07
    0.2%
    1810
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    893
    +0.12
    0.02
    1343
    +0.07
    0.03
    203
    +0.06
    0.02
    Negative Logits
    
    -0.73
    /***
    -0.69
     survive
    -0.60
    bigoplus
    -0.55
    Fuckin
    -0.55
    <tfoot>
    -0.54
    Хро
    -0.54
     disarm
    -0.53
     لينك
    -0.52
     unify
    -0.52
    POSITIVE LOGITS
    bs
    2.51
    BS
    1.89
     bs
    1.53
     BS
    1.29
     Bs
    1.21
    Bs
    1.10
     maroc
    1.02
     Ottobre
    0.99
     Giugno
    0.99
     bds
    0.98
    Activations Density 0.179%

    No Known Activations