© 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. 5325
    Prev
    Next
    INDEX
    Explanations

    references to sampling, testing, and analysis procedures

    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
    554
    +0.12
    0.4%
    896
    +0.10
    0.4%
    1573
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.12
    0.03
    484
    +0.10
    0.02
    896
    +0.10
    0.02
    Negative Logits
     philanth
    -0.73
     seashore
    -0.69
     unlaw
    -0.64
     pamph
    -0.64
     reverend
    -0.61
     unve
    -0.61
    trzyma
    -0.61
    elesaikan
    -0.60
     Mahomet
    -0.59
     nôtre
    -0.59
    POSITIVE LOGITS
     sample
    1.41
     Sample
    1.31
    sample
    1.31
     samples
    1.29
    Sample
    1.25
     SAMPLE
    1.21
    samples
    1.16
     Samples
    1.15
    SAMPLE
    1.15
    Samples
    1.08
    Activations Density 0.075%

    No Known Activations