Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15031
    Prev
    Next
    INDEX
    Explanations

    innovative or significant ideas and discoveries

    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
    1150
    +0.09
    0.3%
    1013
    +0.09
    0.3%
    630
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.09
    0.05
    1786
    +0.09
    0.02
    2030
    +0.09
    0.04
    Negative Logits
     ì
    -0.61
     &___
    -0.56
     congr
    -0.56
     Meksiku
    -0.55
     alp
    -0.55
     Flü
    -0.55
     trattano
    -0.54
     ‹
    -0.54
     ë
    -0.52
     appré
    -0.52
    POSITIVE LOGITS
     McLaugh
    0.78
    yaitu
    0.75
     Vaugh
    0.68
     Constipation
    0.64
    jątk
    0.61
     Namely
    0.61
    awsze
    0.59
     whereby
    0.58
     involving
    0.58
     disreg
    0.57
    Activations Density 0.474%

    No Known Activations