© 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. 5081
    Prev
    Next
    INDEX
    Explanations

    code snippets showcasing coding patterns and examples

    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
    964
    +0.18
    0.5%
    1842
    +0.17
    0.5%
    1445
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.18
    0.04
    453
    +0.17
    0.04
    2002
    +0.14
    0.03
    Negative Logits
     silikon
    -0.59
     plastik
    -0.57
     katastro
    -0.53
     karton
    -0.52
    --){
    -0.52
     biografi
    -0.52
     stadion
    -0.51
     akut
    -0.51
     kokos
    -0.51
     kompres
    -0.51
    POSITIVE LOGITS
     fluo
    0.86
     agi
    0.85
     squa
    0.84
     emphat
    0.83
     emper
    0.82
     fto
    0.82
     effe
    0.81
     surfact
    0.81
     dispen
    0.80
     tetrach
    0.80
    Activations Density 0.295%

    No Known Activations