© 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. 808
    Prev
    Next
    INDEX
    Explanations

    names or abbreviations related to basketball players or teams

    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
    871
    +0.17
    0.7%
    1325
    +0.15
    0.7%
    1482
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.10
    395
    +0.15
    0.07
    227
    +0.15
    0.08
    Negative Logits
    Varför
    -0.58
    Economía
    -0.58
    Från
    -0.52
    comuna
    -0.50
    tamol
    -0.49
     entrou
    -0.48
    Referencer
    -0.47
    Eksteraj
    -0.47
    diğimiz
    -0.47
    Manbalar
    -0.46
    POSITIVE LOGITS
     depic
    0.73
     affor
    0.72
     impra
    0.71
     strick
    0.71
     siff
    0.69
     intersper
    0.69
     chiff
    0.69
     ricardo
    0.67
     GIP
    0.67
     reluct
    0.67
    Activations Density 0.674%

    No Known Activations