© 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. 4081
    Prev
    Next
    INDEX
    Explanations

    references to legal institutions and 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
    1081
    +0.11
    0.3%
    2034
    +0.11
    0.3%
    1870
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.11
    0.07
    1183
    +0.11
    0.04
    1317
    +0.11
    0.06
    Negative Logits
     Ottobre
    -0.76
     Junho
    -0.73
     sappi
    -0.71
     ALLA
    -0.69
     Luglio
    -0.68
     Giugno
    -0.66
     maig
    -0.64
     purtroppo
    -0.61
     Siamo
    -0.59
    Siamo
    -0.58
    POSITIVE LOGITS
     Gorb
    0.87
     Kün
    0.78
     McLaugh
    0.78
     Thacker
    0.74
     Sted
    0.72
     Rine
    0.69
     Schrö
    0.69
     hoody
    0.69
     McInt
    0.68
     Keny
    0.66
    Activations Density 0.363%

    No Known Activations