© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13227
    Prev
    Next
    INDEX
    Explanations

    baseball-related terms and actions

    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
    1870
    +0.11
    0.3%
    868
    +0.10
    0.3%
    2034
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    868
    +0.11
    0.05
    400
    +0.10
    0.04
    756
    +0.10
    0.04
    Negative Logits
     encomp
    -1.19
     intersper
    -1.16
     increa
    -1.09
     reluct
    -1.07
     alberto
    -1.06
     javier
    -1.03
     impra
    -1.01
     sergio
    -0.99
     emphat
    -0.99
     depic
    -0.99
    POSITIVE LOGITS
     gyhoeddwyd
    0.71
     insuffisamment
    0.66
     חיצוניים
    0.66
     تانيه
    0.58
    insee
    0.58
    AsUp
    0.56
     aprilie
    0.56
    úgó
    0.55
    มาะ
    0.55
    UVWXYZ
    0.55
    Activations Density 0.250%

    No Known Activations