© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2073
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1804
    +0.08
    0.2%
    1385
    +0.08
    0.2%
    1445
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.08
    0.04
    1804
    +0.08
    0.04
    1074
    +0.07
    0.04
    Negative Logits
     wien
    -1.02
     fei
    -0.90
     myn
    -0.90
     laun
    -0.88
     „,
    -0.88
     inder
    -0.88
     shenan
    -0.87
     tew
    -0.86
     intersper
    -0.85
     wald
    -0.84
    POSITIVE LOGITS
     totaling
    0.70
    total
    0.66
     total
    0.65
    Total
    0.62
    XMLSchema
    0.60
     cumulative
    0.58
     totalling
    0.58
    getTotal
    0.56
     collectively
    0.55
     totaal
    0.55
    Activations Density 0.251%

    No Known Activations