© 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. 1345
    Prev
    Next
    INDEX
    Explanations

    specific references to drum-related content

    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
    1451
    +0.08
    0.3%
    1806
    +0.08
    0.3%
    732
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1136
    +0.08
    0.02
    91
    +0.08
    0.02
    732
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.66
     inaugurate
    -0.61
    HasColumnType
    -0.54
    HideFlags
    -0.53
    ellular
    -0.52
    
    -0.50
     ratify
    -0.49
     bakal
    -0.49
    AsUp
    -0.48
     reinstate
    -0.47
    POSITIVE LOGITS
     drum
    2.66
     drums
    2.50
     Drum
    2.41
    drum
    2.30
     DRUM
    2.28
    Drum
    2.25
     Drums
    2.24
    drums
    2.17
    Drums
    2.00
     drumming
    1.94
    Activations Density 0.171%

    No Known Activations