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. 15070
    Prev
    Next
    INDEX
    Explanations

    mysteries or unidentified phenomena

    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
    1482
    +0.12
    0.4%
    1103
    +0.11
    0.4%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1443
    +0.12
    0.02
    1103
    +0.11
    0.02
    1482
    +0.10
    0.02
    Negative Logits
     handels
    -0.68
     durs
    -0.62
     vern
    -0.61
     bunda
    -0.60
     donat
    -0.60
     treff
    -0.59
     erk
    -0.59
     folle
    -0.58
     koc
    -0.58
     hek
    -0.57
    POSITIVE LOGITS
     mystery
    1.18
     mysteries
    1.05
    mystery
    1.04
    Mystery
    1.03
     Mystery
    1.02
     mysterious
    0.85
     Mysteries
    0.79
     Mysterious
    0.76
    Mysterious
    0.71
     rencont
    0.68
    Activations Density 0.087%

    No Known Activations