© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6878
    Prev
    Next
    INDEX
    Explanations

    phrases related to brainstorming and generating ideas

    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
    316
    +0.13
    0.5%
    1506
    +0.12
    0.4%
    1983
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.13
    0.04
    1983
    +0.12
    0.03
    240
    +0.11
    0.03
    Negative Logits
     mitte
    -0.81
     pö
    -0.68
     maksi
    -0.67
     väga
    -0.62
     talle
    -0.62
     kait
    -0.57
     pü
    -0.57
     kuni
    -0.57
     jät
    -0.57
     häm
    -0.54
    POSITIVE LOGITS
     idea
    1.25
     Idea
    1.24
     ideas
    1.21
    Idea
    1.18
     Ideas
    1.14
    ideas
    1.12
    Ideas
    1.12
     IDEAS
    1.08
     IDEA
    1.07
    idea
    1.02
    Activations Density 0.068%

    No Known Activations