© 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. 11712
    Prev
    Next
    INDEX
    Explanations

    references to body parts or items linked to personal identity and technology

    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
    1978
    +0.10
    0.3%
    1385
    +0.10
    0.3%
    62
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.10
    0.05
    2044
    +0.10
    0.07
    1317
    +0.09
    0.06
    Negative Logits
     thut
    -0.88
     aen
    -0.81
     intersper
    -0.79
     seiz
    -0.76
     emphat
    -0.76
     excru
    -0.75
     reluct
    -0.74
     Juf
    -0.72
     oner
    -0.72
     fta
    -0.72
    POSITIVE LOGITS
    your
    0.99
     your
    0.99
     yourself
    0.95
     YOUR
    0.92
    Your
    0.90
     Your
    0.90
    yourself
    0.89
    YOUR
    0.80
     yourselves
    0.80
     Yourself
    0.76
    Activations Density 0.614%

    No Known Activations