© 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. 14668
    Prev
    Next
    INDEX
    Explanations

    details related to mechanical parts and components

    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
    1385
    +0.22
    0.7%
    1343
    +0.17
    0.5%
    906
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.22
    0.07
    724
    +0.17
    0.05
    1385
    +0.16
    0.05
    Negative Logits
     praktik
    -1.24
     pessi
    -1.12
     keramik
    -1.07
     Politica
    -1.07
     gend
    -1.06
     socie
    -1.06
     alkoh
    -1.05
     optik
    -1.05
     notor
    -1.05
     protokol
    -1.05
    POSITIVE LOGITS
     człowie
    0.58
     width
    0.56
     amado
    0.55
     vertical
    0.53
     anzunehmen
    0.53
     readline
    0.52
    width
    0.52
     extends
    0.52
     edges
    0.52
    extend
    0.52
    Activations Density 0.351%

    No Known Activations