© 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. 13863
    Prev
    Next
    INDEX
    Explanations

    statistical data and scientific terms related to medical procedures and measurements

    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
    1343
    +0.16
    0.4%
    1699
    +0.12
    0.3%
    876
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.16
    0.03
    956
    +0.12
    0.02
    1151
    +0.12
    0.02
    Negative Logits
     Rodrig
    -0.69
     Horacio
    -0.69
     Cárdenas
    -0.67
     kasarigan
    -0.65
    colourful
    -0.62
     Borja
    -0.62
     Marcela
    -0.62
     Rued
    -0.61
     Reng
    -0.61
     Hermans
    -0.61
    POSITIVE LOGITS
     sensibili
    0.79
     suscit
    0.77
     potest
    0.77
     PREFACE
    0.75
     ejus
    0.73
     habet
    0.71
     eorum
    0.69
     quæ
    0.69
    hahah
    0.67
     giorgio
    0.67
    Activations Density 0.096%

    No Known Activations