© 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. 6636
    Prev
    Next
    INDEX
    Explanations

    mentions of capturing something, be it in a physical or figurative sense

    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
    1512
    +0.13
    0.4%
    316
    +0.10
    0.4%
    1810
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1512
    +0.13
    0.03
    316
    +0.10
    0.02
    1413
    +0.10
    0.02
    Negative Logits
    glied
    -0.47
     Áng
    -0.46
     étu
    -0.45
     saites
    -0.45
    uransi
    -0.44
    wareness
    -0.44
    сылкі
    -0.43
    Encyklopedia
    -0.43
    labus
    -0.43
    modities
    -0.43
    POSITIVE LOGITS
     capture
    1.31
     Capture
    1.25
    capture
    1.22
     captures
    1.20
     captured
    1.16
     capturing
    1.15
    captured
    1.12
     CAPT
    1.08
    Capture
    1.06
    captures
    1.03
    Activations Density 0.070%

    No Known Activations