© 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. 6479
    Prev
    Next
    INDEX
    Explanations

    percentages and statistics presented in text

    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
    674
    +0.10
    0.3%
    303
    +0.08
    0.2%
    1394
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.10
    0.02
    1394
    +0.08
    0.02
    453
    +0.07
    0.03
    Negative Logits
     ecru
    -0.65
     الرياضيه
    -0.60
     softshell
    -0.53
     vellum
    -0.51
     sessile
    -0.51
     hornblende
    -0.50
     trefoil
    -0.50
     incomplète
    -0.49
    calaure
    -0.48
     zirc
    -0.48
    POSITIVE LOGITS
     maksi
    0.68
     akti
    0.59
     affatto
    0.55
     impossibile
    0.52
     augus
    0.51
     sufficiente
    0.50
     chiaramente
    0.50
     haus
    0.49
     riten
    0.49
     chiara
    0.49
    Activations Density 0.130%

    No Known Activations