© 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. 7370
    Prev
    Next
    INDEX
    Explanations

    information or links to stories and resources

    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
    2034
    +0.18
    0.5%
    2019
    +0.17
    0.5%
    382
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    539
    +0.18
    0.03
    62
    +0.17
    0.03
    69
    +0.09
    0.01
    Negative Logits
     lele
    -1.12
     siff
    -1.11
     Traité
    -1.10
     Chapitre
    -1.06
     robus
    -1.06
     Aéroport
    -1.05
     Lég
    -1.05
     endom
    -1.04
     teras
    -1.02
     antik
    -1.01
    POSITIVE LOGITS
     please
    0.90
     visit
    0.72
    please
    0.71
     consider
    0.70
     consult
    0.68
     check
    0.67
     click
    0.66
     you
    0.65
    请
    0.65
     we
    0.65
    Activations Density 0.154%

    No Known Activations