© 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. 1546
    Prev
    Next
    INDEX
    Explanations

    mentions of the schools "Dexter" and "Foxcroft" in relation to wrestling matches

    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
    32
    +0.14
    0.5%
    812
    +0.13
    0.4%
    866
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.04
    690
    +0.13
    0.04
    1363
    +0.12
    0.03
    Negative Logits
    presidente
    -0.61
    ⓧ
    -0.60
    ControllerAdvice
    -0.58
     المعيارى
    -0.58
    ViewFeatures
    -0.58
    rrggbb
    -0.58
    /**
    -0.57
    javac
    -0.56
    ttino
    -0.56
    dubbo
    -0.55
    POSITIVE LOGITS
     Dex
    1.26
     dex
    1.22
     Dexter
    1.21
    dex
    1.20
    Dex
    1.17
     lex
    1.15
     Lex
    1.13
    Lex
    1.07
    Dexter
    1.06
    lex
    1.06
    Activations Density 0.190%

    No Known Activations