© 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. 7210
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their actions, particularly in a news or legal context

    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
    1343
    +0.13
    0.4%
    2011
    +0.11
    0.4%
    596
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1935
    +0.13
    0.03
    1174
    +0.11
    0.02
    474
    +0.10
    0.02
    Negative Logits
    ,
    -0.74
     -
    -0.70
    .
    -0.69
     to
    -0.65
     (
    -0.65
     in
    -0.64
     a
    -0.64
     as
    -0.64
     for
    -0.63
    -
    -0.62
    POSITIVE LOGITS
     silikon
    1.76
     kosme
    1.70
     makro
    1.65
     alkoh
    1.63
     keramik
    1.63
     karton
    1.62
     antik
    1.60
     konkre
    1.59
     kask
    1.59
     kompati
    1.57
    Activations Density 0.040%

    No Known Activations