© 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. 11084
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and buildings

    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
    939
    +0.14
    0.4%
    964
    +0.14
    0.4%
    1120
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.14
    0.08
    817
    +0.14
    0.03
    1804
    +0.12
    0.05
    Negative Logits
     disreg
    -0.98
     lmfao
    -0.98
     subgoals
    -0.89
     😭😭
    -0.86
     apprehen
    -0.86
     fucker
    -0.83
     faggot
    -0.82
     shenan
    -0.80
     ineffec
    -0.78
     downvotes
    -0.76
    POSITIVE LOGITS
     downtown
    0.73
     saurait
    0.67
    <bos>
    0.64
     city
    0.63
     trouvait
    0.59
     Jerusal
    0.57
    Autoritní
    0.57
    Istorija
    0.57
    onViewCreated
    0.57
     situe
    0.56
    Activations Density 0.329%

    No Known Activations