© 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. 13375
    Prev
    Next
    INDEX
    Explanations

    concerns related to health risks and medical interventions

    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
    381
    +0.10
    0.3%
    1809
    +0.09
    0.2%
    1919
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.06
    1415
    +0.09
    0.02
    1809
    +0.07
    0.03
    Negative Logits
     optik
    -0.87
     augus
    -0.85
     galeri
    -0.85
     alpes
    -0.85
     Fasc
    -0.85
     monaster
    -0.85
     lele
    -0.83
     keramik
    -0.82
     antik
    -0.82
     poliester
    -0.81
    POSITIVE LOGITS
    Pozdrawiam
    0.66
     einerseits
    0.59
     sice
    0.58
    lapsingToolbar
    0.58
     nominally
    0.56
     neither
    0.55
    pozdrawiam
    0.55
     atât
    0.54
     arată
    0.54
     își
    0.54
    Activations Density 0.438%

    No Known Activations