© 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. 11738
    Prev
    Next
    INDEX
    Explanations

    numerical values formatted in a specific way

    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
    1967
    +0.10
    0.3%
    1343
    +0.09
    0.3%
    1978
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.10
    0.03
    2002
    +0.09
    0.03
    1343
    +0.09
    0.03
    Negative Logits
     pamph
    -1.13
     shenan
    -1.05
     unwarran
    -1.04
     apprehen
    -1.00
     reluct
    -1.00
     disagre
    -0.99
     McLaugh
    -0.93
     philosophic
    -0.88
     Vaugh
    -0.87
     gaily
    -0.86
    POSITIVE LOGITS
     utop
    0.70
     OMIT
    0.68
     maxime
    0.68
     vola
    0.64
     borsa
    0.61
     cursus
    0.60
     migra
    0.60
     habet
    0.60
     ORGANISM
    0.59
     fuit
    0.59
    Activations Density 0.107%

    No Known Activations