© 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. 12335
    Prev
    Next
    INDEX
    Explanations

    phrases expressing doubt or uncertainty

    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
    1667
    +0.08
    0.2%
    1939
    +0.07
    0.2%
    378
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1417
    +0.08
    0.05
    630
    +0.07
    0.04
    1784
    +0.07
    0.06
    Negative Logits
     Republica
    -0.48
    ndig
    -0.46
    JspWriter
    -0.42
     zob
    -0.41
    memoized
    -0.41
    welijk
    -0.41
     Republi
    -0.41
    ˛
    -0.40
     bambu
    -0.39
    idamente
    -0.39
    POSITIVE LOGITS
     because
    1.50
    because
    1.48
     BECAUSE
    1.27
     becas
    1.25
     becau
    1.25
    Because
    1.22
     Because
    1.16
    ecause
    1.15
     porque
    1.12
     beca
    1.10
    Activations Density 0.800%

    No Known Activations