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. 15338
    Prev
    Next
    INDEX
    Explanations

    structured data representing orders or items in a list

    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
    1978
    +0.13
    0.4%
    1108
    +0.10
    0.3%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1900
    +0.13
    0.04
    1108
    +0.10
    0.05
    499
    +0.10
    0.04
    Negative Logits
     saurait
    -0.78
     trouvera
    -0.76
     reconnaît
    -0.74
     envoie
    -0.73
     accepte
    -0.72
     comprends
    -0.71
     défend
    -0.68
     portait
    -0.68
     répon
    -0.65
     préc
    -0.65
    POSITIVE LOGITS
     isoto
    0.74
     logarith
    0.69
     [{\
    0.64
     synap
    0.64
     lamella
    0.63
     Laplacian
    0.62
     biex
    0.60
     anis
    0.59
     equilibr
    0.59
     vorticity
    0.59
    Activations Density 0.179%

    No Known Activations