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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5646
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical actions and interactions in a narrative

    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
    906
    +0.16
    0.5%
    946
    +0.14
    0.5%
    509
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.16
    0.05
    736
    +0.14
    0.05
    184
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.21
     manuten
    -0.89
     broder
    -0.88
     consoli
    -0.80
     roba
    -0.79
     ciment
    -0.78
     pép
    -0.78
     miniatura
    -0.78
     pét
    -0.77
     prodi
    -0.76
    POSITIVE LOGITS
     McLaugh
    0.73
     McInt
    0.70
     Vaugh
    0.65
     stratigraph
    0.62
     shewn
    0.61
     Bartholo
    0.60
     poetical
    0.58
     unlaw
    0.57
     Shreve
    0.56
     incoherent
    0.56
    Activations Density 0.174%

    No Known Activations