© 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. 12099
    Prev
    Next
    INDEX
    Explanations

    links or prompts to watch or check out various content or information

    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
    1350
    +0.17
    0.7%
    1133
    +0.14
    0.5%
    481
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1133
    +0.17
    0.04
    1350
    +0.14
    0.04
    1356
    +0.12
    0.03
    Negative Logits
     hek
    -0.54
     mily
    -0.51
     erk
    -0.51
     dolar
    -0.49
     ideolog
    -0.49
     hiper
    -0.49
     bunda
    -0.48
     balkon
    -0.47
     sej
    -0.47
    €
    -0.46
    POSITIVE LOGITS
     watch
    1.30
     Watch
    1.21
    watch
    1.19
     watches
    1.19
     Watched
    1.16
     watched
    1.12
     WATCH
    1.11
     shenan
    1.11
     Watching
    1.10
    Watch
    1.09
    Activations Density 0.104%

    No Known Activations