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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15203
    Prev
    Next
    INDEX
    Explanations

    instances of the word "variety."

    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
    1921
    +0.16
    0.6%
    871
    +0.14
    0.5%
    1865
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.16
    0.03
    1865
    +0.14
    0.02
    871
    +0.13
    0.03
    Negative Logits
     Román
    -0.58
     foton
    -0.58
     Belén
    -0.57
     Áng
    -0.56
     häm
    -0.53
     Héctor
    -0.53
    Kaip
    -0.52
    Nuorodos
    -0.52
     Cuen
    -0.51
     silikon
    -0.51
    POSITIVE LOGITS
     actionTypes
    0.93
     Variety
    0.84
     variety
    0.84
    variety
    0.82
     varieties
    0.81
     pymysql
    0.78
     variation
    0.78
     vary
    0.77
     VARI
    0.77
     variations
    0.75
    Activations Density 0.076%

    No Known Activations