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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12833
    Prev
    Next
    INDEX
    Explanations

    details about sports players and their performances

    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
    625
    +0.10
    0.3%
    121
    +0.09
    0.3%
    1798
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1689
    +0.10
    0.04
    1551
    +0.09
    0.04
    121
    +0.07
    0.04
    Negative Logits
     disbur
    -0.55
    AfterClass
    -0.55
     volk
    -0.50
     zand
    -0.46
    RECOMMENDATIONS
    -0.43
     userEmail
    -0.42
     problemów
    -0.42
     koel
    -0.41
     interfacial
    -0.41
    jącą
    -0.40
    POSITIVE LOGITS
     kön
    0.79
     Valentín
    0.76
     Áng
    0.73
     Compañ
    0.73
     Portugu
    0.73
    /−
    0.70
     Chá
    0.70
     pernic
    0.70
     interro
    0.70
     contrari
    0.68
    Activations Density 0.343%

    No Known Activations