© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 324
    Prev
    Next
    INDEX
    Explanations

    references to specific player names and positions in a sports context

    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
    1407
    +0.12
    0.4%
    1092
    +0.11
    0.3%
    555
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.05
    690
    +0.11
    0.06
    1343
    +0.09
    0.05
    Negative Logits
    <bos>
    -0.72
     atque
    -0.60
     rerum
    -0.59
    ніципалі
    -0.57
     tehd
    -0.55
    denim
    -0.54
    OrNil
    -0.54
    wikidata
    -0.54
    fristi
    -0.53
    roughts
    -0.52
    POSITIVE LOGITS
     Levit
    1.41
     Kap
    1.21
    Kap
    1.12
     Kaplan
    1.06
     lamborghini
    1.00
     gsx
    0.97
     gim
    0.97
     fup
    0.96
     levit
    0.95
     Kah
    0.94
    Activations Density 0.338%

    No Known Activations