© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13810
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to movies, individuals, and concepts

    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
    1978
    +0.12
    0.3%
    1150
    +0.09
    0.3%
    394
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.12
    0.04
    227
    +0.09
    0.07
    764
    +0.09
    0.05
    Negative Logits
     autorytatywna
    -0.93
    脚注の使い方
    -0.85
     تضيفلها
    -0.84
    Autoritní
    -0.79
     exé
    -0.79
    IndentedString
    -0.78
     مرئيه
    -0.77
     étu
    -0.76
     quegli
    -0.74
    GEBURTSDATUM
    -0.73
    POSITIVE LOGITS
    Grath
    0.50
    姆斯
    0.50
     variant
    0.49
     that
    0.47
    UpdatedBy
    0.47
     çünkü
    0.47
     existence
    0.47
     incarnation
    0.47
     iteration
    0.46
     wzór
    0.46
    Activations Density 0.501%

    No Known Activations