© 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. 14701
    Prev
    Next
    INDEX
    Explanations

    time-related events or experiences

    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
    +0.15
    0.5%
    1376
    +0.13
    0.4%
    1194
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.15
    0.03
    1194
    +0.13
    0.03
    1135
    +0.11
    0.03
    Negative Logits
    Estilo
    -0.61
    Diret
    -0.56
    Continu
    -0.56
    detal
    -0.55
     Febrero
    -0.55
    Loja
    -0.55
    Abril
    -0.54
    Ofer
    -0.54
    databinding
    -0.54
    Avez
    -0.54
    POSITIVE LOGITS
     maneu
    0.86
     reluct
    0.86
     ago
    0.85
     gaily
    0.83
     reconno
    0.83
     fep
    0.82
     milf
    0.81
     Pamphlet
    0.81
     ftu
    0.81
     disagre
    0.80
    Activations Density 0.073%

    No Known Activations