© 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. 11772
    Prev
    Next
    INDEX
    Explanations

    dates and durations in years

    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
    1967
    +0.11
    0.3%
    776
    +0.11
    0.3%
    674
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.11
    0.06
    776
    +0.11
    0.05
    1295
    +0.10
    0.04
    Negative Logits
     friable
    -0.74
     impractica
    -0.68
     luxuriant
    -0.66
     loveliness
    -0.63
     anhyd
    -0.62
     consummation
    -0.61
    harmed
    -0.61
     linden
    -0.60
     barbarous
    -0.59
     overhanging
    -0.59
    POSITIVE LOGITS
     alkoh
    1.11
     marte
    1.05
     meras
    1.03
     incess
    1.01
     manuten
    0.95
     solidar
    0.94
     biograf
    0.94
     utop
    0.92
     republi
    0.92
     spion
    0.92
    Activations Density 0.152%

    No Known Activations