© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    references to different types of vessels, such as ships and boats

    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
    1758
    +0.11
    0.3%
    1983
    +0.09
    0.3%
    893
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1983
    +0.11
    0.02
    1758
    +0.09
    0.02
    12
    +0.09
    0.02
    Negative Logits
    ⓧ
    -0.63
    はじめに
    -0.53
    StartTag
    -0.53
    aarrggbb
    -0.51
    },{
    -0.51
    noStroke
    -0.50
    fseek
    -0.50
    ništ
    -0.50
    <_>
    -0.50
    spesies
    -0.49
    POSITIVE LOGITS
     vessel
    2.51
     vessels
    2.44
     Vessels
    2.38
     Vessel
    2.36
    vessel
    2.20
    Vessel
    2.16
    vessels
    2.02
     isuzu
    1.06
     chrysler
    1.04
     vasi
    1.04
    Activations Density 0.210%

    No Known Activations