© 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. 11499
    Prev
    Next
    INDEX
    Explanations

    steps or instructions in a process

    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
    964
    +0.13
    0.4%
    1577
    +0.12
    0.4%
    381
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.13
    0.04
    2044
    +0.12
    0.12
    62
    +0.11
    0.07
    Negative Logits
     dises
    -1.28
     fta
    -1.23
     magis
    -1.21
     aen
    -1.20
     thut
    -1.19
     ftu
    -1.18
     haup
    -1.13
     fup
    -1.12
     fep
    -1.11
     erec
    -1.11
    POSITIVE LOGITS
     wondering
    0.83
     my
    0.76
     I
    0.74
     hoping
    0.74
     want
    0.71
     please
    0.69
     am
    0.68
     hopefully
    0.67
     myself
    0.67
     me
    0.66
    Activations Density 2.271%

    No Known Activations