© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7464
    Prev
    Next
    INDEX
    Explanations

    cooking instructions for preparing tofu dishes

    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
    876
    +0.17
    0.5%
    381
    +0.13
    0.4%
    1013
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.17
    0.02
    1014
    +0.13
    0.02
    1388
    +0.12
    0.01
    Negative Logits
     courtiers
    -0.71
     pamph
    -0.71
     vainly
    -0.69
     unwarran
    -0.68
    alnız
    -0.67
     pymongo
    -0.65
     vicissitudes
    -0.65
     moeili
    -0.64
    forhold
    -0.63
     dår
    -0.63
    POSITIVE LOGITS
     meis
    0.93
     FEBR
    0.89
     NOO
    0.85
     nutr
    0.84
     inder
    0.84
     karton
    0.82
     affez
    0.82
     ananas
    0.80
     palet
    0.80
     zom
    0.79
    Activations Density 0.073%

    No Known Activations