© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13733
    Prev
    Next
    INDEX
    Explanations

    descriptions related to food recipes

    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
    2034
    +0.17
    0.5%
    2019
    +0.11
    0.4%
    1042
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.17
    0.05
    490
    +0.11
    0.04
    1537
    +0.11
    0.05
    Negative Logits
     dises
    -1.65
     mef
    -1.58
     ordina
    -1.56
     dispen
    -1.55
     fta
    -1.53
     robus
    -1.53
     sopr
    -1.51
     lill
    -1.48
     sappi
    -1.48
     nutr
    -1.47
    POSITIVE LOGITS
     you
    0.98
     or
    0.88
     please
    0.86
     there
    0.82
     it
    0.81
     don
    0.81
     then
    0.78
     или
    0.78
     consider
    0.77
     we
    0.76
    Activations Density 0.196%

    No Known Activations