© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6846
    Prev
    Next
    INDEX
    Explanations

    alphabetical lists

    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
    50
    +0.23
    0.8%
    394
    +0.19
    0.6%
    764
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.23
    0.06
    612
    +0.19
    0.01
    394
    +0.15
    0.05
    Negative Logits
    mability
    -0.54
    [*
    -0.49
    pography
    -0.49
     hombros
    -0.48
    venido
    -0.48
     amplit
    -0.48
    iphery
    -0.47
    GRAPHICAL
    -0.47
     espac
    -0.46
     tré
    -0.46
    POSITIVE LOGITS
     McLaugh
    1.18
     unlaw
    1.06
     Perci
    1.04
     McInt
    1.01
     unspeak
    1.00
     Bartholo
    0.99
     Gorb
    0.95
     Jusqu
    0.95
     pamph
    0.93
     swarovski
    0.92
    Activations Density 0.609%

    No Known Activations