© 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. 12178
    Prev
    Next
    INDEX
    Explanations

    features and functions of a digital service or app

    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
    381
    +0.12
    0.4%
    764
    +0.11
    0.3%
    478
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.12
    0.04
    289
    +0.11
    0.03
    185
    +0.11
    0.03
    Negative Logits
    ubakar
    -0.65
    Diweddarwch
    -0.58
    minHeight
    -0.54
    adaş
    -0.54
    vailability
    -0.53
     ibang
    -0.51
    onBlur
    -0.50
    cún
    -0.50
    dropIfExists
    -0.49
     bawat
    -0.49
    POSITIVE LOGITS
     strick
    1.06
     perfet
    1.06
     guarante
    1.05
     purcha
    1.03
     beaut
    1.02
     greate
    1.02
     milf
    1.01
     alre
    1.00
     fuf
    1.00
     laun
    0.97
    Activations Density 0.321%

    No Known Activations