© 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. 7149
    Prev
    Next
    INDEX
    Explanations

    phrases related to operations and procedures, specifically focusing on creating and managing operations

    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
    1276
    +0.13
    0.5%
    438
    +0.12
    0.4%
    1870
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.13
    0.03
    1092
    +0.12
    0.03
    78
    +0.11
    0.03
    Negative Logits
    rungsseite
    -0.51
     Lungen
    -0.50
    ☞
    -0.45
     ital
    -0.42
    inição
    -0.42
    tats
    -0.42
    imab
    -0.42
    anthin
    -0.42
    iff
    -0.42
    ZIL
    -0.41
    POSITIVE LOGITS
     Operate
    1.28
     hairc
    1.16
     Operated
    1.07
     Operating
    1.07
     swarovski
    1.05
     operating
    1.05
    operate
    1.05
    operating
    1.03
     operated
    1.02
     operate
    1.02
    Activations Density 0.072%

    No Known Activations