© 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 EvalsExportsinterp-engineNEWAPI 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. 10667
    Prev
    Next
    INDEX
    Explanations

    URLs starting with 'http://' and 'https://'

    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
    1741
    +0.18
    0.6%
    1343
    +0.15
    0.5%
    2034
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.18
    0.03
    733
    +0.15
    0.03
    851
    +0.14
    0.02
    Negative Logits
     ClassNotFound
    -0.63
     зустрі
    -0.63
     FontFamily
    -0.62
     іде
    -0.61
     rağmen
    -0.61
     сьогодні
    -0.60
    aniline
    -0.59
     втра
    -0.58
    membrance
    -0.58
     to
    -0.57
    POSITIVE LOGITS
     seiz
    1.38
     dises
    1.35
     opport
    1.33
     wherea
    1.30
     peculi
    1.27
     effe
    1.25
     dispen
    1.25
     ivi
    1.25
     »>
    1.24
     oner
    1.24
    Activations Density 0.033%

    No Known Activations