© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11013
    Prev
    Next
    INDEX
    Explanations

    quotations and statements made with strong opinions or assertions

    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
    674
    +0.17
    0.5%
    1052
    +0.13
    0.4%
    892
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1052
    +0.17
    0.04
    31
    +0.13
    0.02
    892
    +0.11
    0.03
    Negative Logits
     embra
    -1.34
     fta
    -1.30
     effe
    -1.27
     increa
    -1.27
     emphat
    -1.26
     Augu
    -1.26
     depic
    -1.25
     squa
    -1.25
     mef
    -1.25
     affor
    -1.24
    POSITIVE LOGITS
     “
    0.67
     "
    0.60
    “
    0.58
     because
    0.57
    but
    0.57
     but
    0.57
    ，“
    0.56
     «
    0.55
    while
    0.52
    đi
    0.52
    Activations Density 0.139%

    No Known Activations