© 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. 14888
    Prev
    Next
    INDEX
    Explanations

    statistical measurements and comparisons between different groups or categories

    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
    674
    +0.15
    0.4%
    1343
    +0.10
    0.3%
    1009
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1009
    +0.15
    0.03
    1180
    +0.10
    0.03
    1511
    +0.08
    0.02
    Negative Logits
     McLaugh
    -0.72
     Vaugh
    -0.67
     Cuth
    -0.65
     Shreve
    -0.62
     McInt
    -0.59
     Rine
    -0.58
     hacienda
    -0.58
     Thier
    -0.55
     Daven
    -0.55
     Knud
    -0.55
    POSITIVE LOGITS
     créateur
    0.76
     Hvad
    0.75
     bénéficiaire
    0.72
     Secrétaire
    0.70
     gti
    0.69
     Ottobre
    0.69
     veu
    0.68
     découver
    0.67
     poète
    0.64
     vété
    0.64
    Activations Density 0.040%

    No Known Activations