© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4417
    Prev
    Next
    INDEX
    Explanations

    references to specific textual sources

    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
    +0.21
    0.7%
    50
    +0.17
    0.6%
    1967
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.21
    0.06
    401
    +0.17
    0.05
    16
    +0.15
    0.07
    Negative Logits
     tramonto
    -0.70
    ==""){
    -0.67
     stuks
    -0.66
    =="")
    -0.61
    idać
    -0.61
    niosek
    -0.60
     soeur
    -0.59
    ">:
    -0.58
    ">...
    -0.56
     saluti
    -0.54
    POSITIVE LOGITS
     pié
    0.66
     midst
    0.63
     ideolog
    0.63
     robus
    0.61
     hoj
    0.59
     Alfons
    0.58
     Fö
    0.58
     Verk
    0.56
     vicinity
    0.56
     solidar
    0.55
    Activations Density 0.341%

    No Known Activations