© 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. 12381
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and developments

    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
    394
    +0.23
    0.7%
    856
    +0.12
    0.4%
    612
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.23
    0.02
    1904
    +0.12
    0.04
    184
    +0.10
    0.01
    Negative Logits
     bont
    -0.74
     gmbh
    -0.72
     integrale
    -0.71
     sfera
    -0.69
     ananas
    -0.69
     luxem
    -0.68
     sfer
    -0.66
     lpg
    -0.66
     venez
    -0.65
     utop
    -0.64
    POSITIVE LOGITS
    Economía
    0.56
    Eventually
    0.55
     hashlib
    0.54
     pymysql
    0.53
    četně
    0.53
    Географиясе
    0.52
     îna
    0.52
     nasled
    0.52
    ביוגרפיה
    0.51
     became
    0.51
    Activations Density 0.504%

    No Known Activations