© 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. 10578
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences asking about various scenarios or actions

    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
    1101
    +0.13
    0.4%
    1926
    +0.11
    0.3%
    61
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.13
    0.05
    36
    +0.11
    0.04
    1926
    +0.10
    0.04
    Negative Logits
     Doğ
    -0.59
     Söz
    -0.51
     İlk
    -0.50
     Özel
    -0.50
     Çok
    -0.49
     produrre
    -0.49
     Eğ
    -0.47
     akade
    -0.46
    QMetaType
    -0.44
     Tüm
    -0.44
    POSITIVE LOGITS
    sightly
    0.70
    mistak
    0.57
     HOW
    0.56
    howto
    0.55
     how
    0.54
    HOW
    0.53
    wavering
    0.52
     NTIS
    0.52
     ristoranti
    0.51
     angela
    0.50
    Activations Density 0.180%

    No Known Activations