© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4160
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to health and research studies

    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
    678
    +0.10
    0.3%
    1081
    +0.10
    0.3%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    577
    +0.10
    0.08
    1304
    +0.10
    0.07
    227
    +0.10
    0.08
    Negative Logits
     suchte
    -0.69
    película
    -0.61
     glaubte
    -0.58
    Карьера
    -0.58
    bringt
    -0.57
    AxisAlignment
    -0.56
    FontOfSize
    -0.54
    Iglesia
    -0.54
     verfol
    -0.54
     muchacha
    -0.53
    POSITIVE LOGITS
     stockholm
    1.36
     wien
    1.33
     milano
    1.31
     frankfurt
    1.29
     Cfr
    1.28
     suspic
    1.28
     salomon
    1.27
     budapest
    1.26
     napoli
    1.26
     casio
    1.25
    Activations Density 0.452%

    No Known Activations