© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6963
    Prev
    Next
    INDEX
    Explanations

    addresses and contact information

    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
    1343
    +0.16
    0.5%
    1741
    +0.11
    0.3%
    964
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.16
    0.03
    1186
    +0.11
    0.02
    817
    +0.11
    0.02
    Negative Logits
     disreg
    -0.74
     cabrio
    -0.71
     catast
    -0.70
     inappro
    -0.69
     immor
    -0.67
     tupperware
    -0.66
     emphat
    -0.65
     pessi
    -0.65
     arbitrar
    -0.65
     abbiano
    -0.65
    POSITIVE LOGITS
     plongée
    0.58
     montée
    0.56
     vérification
    0.55
     confé
    0.55
     stationnement
    0.55
     tungkol
    0.53
     plancher
    0.53
     congrès
    0.53
     célé
    0.53
     verrou
    0.52
    Activations Density 0.076%

    No Known Activations