© 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. 6972
    Prev
    Next
    INDEX
    Explanations

    names and specific terms related to various individuals and characters

    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
    1741
    +0.14
    0.6%
    144
    +0.12
    0.5%
    1177
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.14
    0.03
    1387
    +0.12
    0.03
    545
    +0.12
    0.03
    Negative Logits
     egyszer
    -0.54
     odpowiedzi
    -0.50
    část
    -0.50
     poby
    -0.49
     نيوز
    -0.49
     wspar
    -0.49
     święta
    -0.49
     odpowiedzial
    -0.48
     betreffenden
    -0.47
     tě
    -0.47
    POSITIVE LOGITS
     John
    1.36
    John
    1.32
     Sén
    1.30
     john
    1.25
     Châ
    1.23
     Traité
    1.21
     JOHN
    1.21
     alkoh
    1.20
    JOHN
    1.18
     kön
    1.15
    Activations Density 0.083%

    No Known Activations