© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    information related to events, contests, and promotions

    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
    188
    +0.15
    0.5%
    1392
    +0.15
    0.5%
    1757
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1392
    +0.15
    0.04
    188
    +0.15
    0.03
    1757
    +0.13
    0.03
    Negative Logits
    Argumento
    -0.60
    mListener
    -0.60
    tau
    -0.58
    progressDialog
    -0.55
    Análisis
    -0.54
    Ainda
    -0.54
    pal
    -0.54
    Dirección
    -0.53
    resizeMode
    -0.52
    Estad
    -0.52
    POSITIVE LOGITS
     viciss
    1.47
     reluct
    1.31
     sergio
    1.28
     bourgeo
    1.27
     encomp
    1.25
     increa
    1.24
     swarovski
    1.24
     jorge
    1.24
     Intere
    1.23
     affor
    1.23
    Activations Density 0.049%

    No Known Activations