© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3747
    Prev
    Next
    INDEX
    Explanations

    the word "chicken" and related terms such as "fingers," "poultry," "roosters," and "nuggets."

    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
    331
    +0.15
    0.6%
    757
    +0.14
    0.6%
    896
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.15
    0.02
    757
    +0.14
    0.02
    1557
    +0.13
    0.02
    Negative Logits
     oreo
    -0.82
     nutella
    -0.81
     peppa
    -0.78
     pican
    -0.73
     perciò
    -0.72
     Così
    -0.71
     gius
    -0.69
    ougars
    -0.69
     !...
    -0.68
     noel
    -0.68
    POSITIVE LOGITS
     chicken
    1.43
     Chicken
    1.31
    chicken
    1.24
     chickens
    1.24
    Chicken
    1.21
     poultry
    0.95
     CHICKEN
    0.95
     Hen
    0.91
     Chickens
    0.90
     hen
    0.87
    Activations Density 0.094%

    No Known Activations