© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10585
    Prev
    Next
    INDEX
    Explanations

    and activate on SQL-related words and commands

    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
    876
    +0.16
    0.5%
    1150
    +0.13
    0.4%
    1699
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.16
    0.00
    1871
    +0.13
    0.03
    1317
    +0.11
    0.03
    Negative Logits
    Geografi
    -0.63
    Dá
    -0.63
    Fontes
    -0.59
    formulario
    -0.59
    Große
    -0.58
    Sinopsis
    -0.58
    Tó
    -0.56
    Atlético
    -0.56
    Apesar
    -0.56
    Avantages
    -0.55
    POSITIVE LOGITS
     effe
    1.42
     oner
    1.38
     increa
    1.37
     unil
    1.36
     illi
    1.35
     guarante
    1.33
     deleter
    1.33
     wong
    1.32
     igno
    1.30
     ritard
    1.29
    Activations Density 0.081%

    No Known Activations