© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software updates and bug fixes

    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
    262
    +0.09
    0.2%
    1919
    +0.07
    0.2%
    1536
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.09
    0.05
    198
    +0.07
    0.04
    1249
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.86
    RegressionTest
    -0.65
    Демографія
    -0.57
    Styleable
    -0.50
    matchCondition
    -0.50
    writeFieldEnd
    -0.50
     <=",
    -0.49
    Notae
    -0.49
    хьтан
    -0.49
     bağlantılar
    -0.49
    POSITIVE LOGITS
     previously
    1.08
    previously
    1.04
     heretofore
    1.02
     hitherto
    0.96
     Previously
    0.90
    Previously
    0.84
     previous
    0.81
     PREVIOUS
    0.80
     Previous
    0.75
     muna
    0.74
    Activations Density 0.418%

    No Known Activations