© 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. 1912
    Prev
    Next
    INDEX
    Explanations

    information related to laws or regulations

    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
    1265
    +0.12
    0.4%
    382
    +0.11
    0.3%
    1173
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.12
    0.04
    1173
    +0.11
    0.04
    1757
    +0.10
    0.04
    Negative Logits
     lele
    -1.56
     mef
    -1.34
     istan
    -1.29
     kasa
    -1.29
     hina
    -1.29
     makro
    -1.28
     antik
    -1.27
     sement
    -1.22
     parati
    -1.22
     gend
    -1.21
    POSITIVE LOGITS
    ,
    0.65
     therefore
    0.61
     however
    0.60
     ,
    0.58
     indeed
    0.58
     mówią
    0.56
     literally
    0.55
     uh
    0.55
     perhaps
    0.54
     or
    0.53
    Activations Density 0.149%

    No Known Activations