© 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. 14782
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving multiplication and division

    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
    876
    +0.16
    0.5%
    1385
    +0.13
    0.4%
    1978
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.16
    0.04
    876
    +0.13
    -0.00
    609
    +0.12
    0.03
    Negative Logits
     shenan
    -1.14
     endeavouring
    -1.11
     philanth
    -1.08
     unspeak
    -1.08
     horrend
    -1.02
     pamph
    -1.02
     apprehen
    -0.99
     sophistic
    -0.98
     endeav
    -0.95
     salutary
    -0.93
    POSITIVE LOGITS
     chèvre
    0.91
     auguri
    0.91
     dì
    0.88
     jacques
    0.87
     bandai
    0.87
     LIRE
    0.86
     espé
    0.84
     nutella
    0.83
    {?>
    0.83
     luy
    0.83
    Activations Density 0.191%

    No Known Activations