© 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. 12508
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical characteristics and materials

    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
    468
    +0.13
    0.4%
    906
    +0.11
    0.3%
    776
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.13
    0.08
    468
    +0.11
    0.05
    671
    +0.10
    0.04
    Negative Logits
     hairc
    -0.70
     swarovski
    -0.63
     isolato
    -0.60
     eccellente
    -0.59
     voleva
    -0.58
     chande
    -0.57
     tiffany
    -0.57
     affez
    -0.57
     parteci
    -0.57
     embra
    -0.57
    POSITIVE LOGITS
     mysterious
    0.82
     mystery
    0.78
     unidentified
    0.76
     unknown
    0.74
    sterious
    0.72
     strange
    0.69
    mystery
    0.65
    unknown
    0.59
     suspicious
    0.59
     unexplained
    0.57
    Activations Density 1.146%

    No Known Activations