© 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. 10674
    Prev
    Next
    INDEX
    Explanations

    academic and scholarly terms

    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
    1096
    +0.14
    0.6%
    410
    +0.12
    0.5%
    1691
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.14
    0.02
    1096
    +0.12
    0.02
    991
    +0.11
    0.02
    Negative Logits
    Aholisi
    -0.53
    EndInit
    -0.52
    djangoproject
    -0.52
    inição
    -0.51
     uLocal
    -0.50
    UnitTesting
    -0.50
     وتسجيلات
    -0.50
    FlatAppearance
    -0.49
    WireFormatLite
    -0.49
    KURZBESCHREIBUNG
    -0.48
    POSITIVE LOGITS
     scholarship
    1.22
     scholar
    1.17
     scholars
    1.13
    Scholars
    1.13
     Scholars
    1.10
     Scholarship
    1.09
    scholars
    1.06
     SCHOLAR
    1.06
     scholarships
    1.05
     Scholar
    1.05
    Activations Density 0.092%

    No Known Activations