Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15002
    Prev
    Next
    INDEX
    Explanations

    references to historical events and geographical locations

    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
    599
    +0.31
    1.2%
    964
    +0.27
    1.1%
    764
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.31
    0.06
    964
    +0.27
    0.03
    1804
    +0.17
    0.03
    Negative Logits
    ImageBackground
    -0.45
    shadowOffset
    -0.45
    fillText
    -0.44
     Winaray
    -0.43
    IsNotEmpty
    -0.42
    btnClose
    -0.41
    btnBack
    -0.41
    subfigure
    -0.41
    XmlEnum
    -0.40
    btnDelete
    -0.39
    POSITIVE LOGITS
    ighborhood
    0.58
     Allegretto
    0.58
     ivelany
    0.56
    izational
    0.55
     »>
    0.54
     ftu
    0.54
     congr
    0.53
     blackpink
    0.53
    dafx
    0.53
    ghijkl
    0.53
    Activations Density 0.241%

    No Known Activations