© 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. 12920
    Prev
    Next
    INDEX
    Explanations

    dates and events related to historical or specific occurrences

    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
    776
    +0.14
    0.4%
    1177
    +0.12
    0.3%
    332
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.14
    0.06
    937
    +0.12
    0.05
    393
    +0.10
    0.05
    Negative Logits
     referenties
    -0.69
    IsMutable
    -0.68
    DoubleQuotes
    -0.66
     pinulongan
    -0.65
    <bos>
    -0.65
    RegressionTest
    -0.64
    клопе
    -0.64
    tadır
    -0.63
     CreateTagHelper
    -0.60
    InstrumentedTest
    -0.59
    POSITIVE LOGITS
     maneu
    0.77
     Frö
    0.75
     Standardi
    0.74
     excru
    0.72
    mainwindow
    0.71
     délib
    0.70
     Ferdin
    0.70
     conftest
    0.69
     Duisburg
    0.67
     Boek
    0.67
    Activations Density 0.130%

    No Known Activations