© 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. 15212
    Prev
    Next
    INDEX
    Explanations

    numbers in the text

    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
    1978
    +0.12
    0.3%
    776
    +0.11
    0.3%
    227
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1435
    +0.12
    0.05
    321
    +0.11
    0.05
    1105
    +0.11
    0.04
    Negative Logits
     Ottobre
    -0.93
     Luglio
    -0.79
     Giugno
    -0.78
     Settembre
    -0.74
    strona
    -0.66
    Πηγές
    -0.66
    Și
    -0.62
    nasel
    -0.61
     dovr
    -0.60
    ἐ
    -0.59
    POSITIVE LOGITS
    0
    0.56
    4
    0.54
    8
    0.54
    5
    0.54
    6
    0.53
    7
    0.53
     kredi
    0.52
    3
    0.52
     Respectfully
    0.52
    9
    0.50
    Activations Density 0.123%

    No Known Activations