© 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. 11225
    Prev
    Next
    INDEX
    Explanations

    mentions of software features or updates

    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
    678
    +0.16
    0.5%
    876
    +0.14
    0.4%
    906
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.16
    0.05
    1254
    +0.14
    0.04
    1403
    +0.12
    0.01
    Negative Logits
     Timoteo
    -0.84
     Darío
    -0.79
     Asunción
    -0.79
     Sarmiento
    -0.73
     xxv
    -0.73
     xxvi
    -0.72
     Cádiz
    -0.72
     Belén
    -0.72
     Shakspeare
    -0.71
     Morelos
    -0.71
    POSITIVE LOGITS
     vola
    0.84
     zom
    0.77
     palet
    0.70
     utop
    0.70
     boxe
    0.69
     bont
    0.67
    woor
    0.66
     ovale
    0.65
     VERTICAL
    0.65
     canne
    0.65
    Activations Density 0.331%

    No Known Activations