© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3931
    Prev
    Next
    INDEX
    Explanations

    language related to political, medical or athletic activities

    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
    50
    +0.20
    0.7%
    1177
    +0.13
    0.5%
    453
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1762
    +0.20
    0.06
    361
    +0.13
    0.06
    270
    +0.13
    0.07
    Negative Logits
    <bos>
    -1.61
    ⓧ
    -0.74
    <?
    -0.55
    /**
    -0.55
    
    
    -0.54
    WithMany
    -0.52
    /*
    -0.52
    pexpr
    -0.52
    blico
    -0.51
    .
    -0.49
    POSITIVE LOGITS
     strick
    1.65
     maneu
    1.65
     increa
    1.64
     scrat
    1.58
     gaily
    1.58
     reluct
    1.55
     tolerably
    1.54
     depic
    1.53
     disagre
    1.51
     unden
    1.51
    Activations Density 1.592%

    No Known Activations