© 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 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. 5869
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers or quantities

    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
    599
    +0.15
    0.5%
    1343
    +0.12
    0.4%
    872
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.15
    0.08
    845
    +0.12
    0.04
    184
    +0.11
    0.01
    Negative Logits
     дописавши
    -0.97
    abestanden
    -0.65
    parsedMessage
    -0.60
    bewerken
    -0.57
    Externí
    -0.57
    <eos>
    -0.52
    Välislingid
    -0.51
    Havolalar
    -0.50
     الحره
    -0.49
     resourceCulture
    -0.48
    POSITIVE LOGITS
     débris
    0.83
     (…)
    0.83
     (...)
    0.73
     [...]
    0.68
     [...
    0.66
     shippuden
    0.65
     ?...
    0.64
    hematical
    0.63
     🤣🤣
    0.63
    arture
    0.63
    Activations Density 0.787%

    No Known Activations