© 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. 282
    Prev
    Next
    INDEX
    Explanations

    information related to sports games, including scores, player statistics, and game outcomes

    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
    1520
    +0.07
    0.2%
    328
    +0.07
    0.2%
    943
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.07
    0.04
    1363
    +0.07
    0.03
    81
    +0.07
    0.02
    Negative Logits
    ⓧ
    -0.67
    <?
    -0.59
    Fg
    -0.57
    /***
    -0.57
    Manufact
    -0.56
    daos
    -0.56
    DTOs
    -0.56
    
    -0.54
    šech
    -0.53
    strona
    -0.52
    POSITIVE LOGITS
     halftime
    2.44
     intermission
    1.15
     pamph
    0.90
     thuy
    0.89
    fordable
    0.77
     offseason
    0.74
     Nguy
    0.74
     cavallo
    0.74
     sirup
    0.74
     fuo
    0.74
    Activations Density 0.307%

    No Known Activations