© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7238
    Prev
    Next
    INDEX
    Explanations

    websites and software tools

    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
    382
    +0.14
    0.5%
    1896
    +0.13
    0.4%
    1535
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.14
    0.03
    382
    +0.13
    0.04
    1271
    +0.13
    0.04
    Negative Logits
     unspeak
    -1.28
     shenan
    -1.27
     intersper
    -1.22
     apprehen
    -1.15
     disreg
    -1.08
     encomp
    -1.07
     indescri
    -1.07
     hairc
    -1.06
     horrend
    -1.06
     indestru
    -1.05
    POSITIVE LOGITS
     handels
    0.75
     vermel
    0.75
     trö
    0.73
     kosme
    0.71
     marte
    0.68
     skak
    0.68
    Etimo
    0.68
    Trama
    0.67
     <",
    0.65
    naio
    0.65
    Activations Density 0.169%

    No Known Activations