© 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. 6834
    Prev
    Next
    INDEX
    Explanations

    terms related to photography equipment and settings

    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
    1624
    +0.17
    0.6%
    1491
    +0.12
    0.4%
    1678
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1624
    +0.17
    0.03
    789
    +0.12
    0.03
    1491
    +0.11
    0.02
    Negative Logits
     vorrei
    -0.83
     poichè
    -0.79
     javier
    -0.79
     claudia
    -0.79
     tanga
    -0.79
     unlaw
    -0.78
     mof
    -0.77
     sergio
    -0.76
     burberry
    -0.75
     alberto
    -0.75
    POSITIVE LOGITS
     camera
    1.46
    camera
    1.35
     cameras
    1.34
     Camera
    1.34
    Camera
    1.23
     Cameras
    1.09
     CAMERA
    1.03
    cameras
    1.03
    CAMERA
    1.02
    Cameras
    1.00
    Activations Density 0.047%

    No Known Activations