© 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. 6030
    Prev
    Next
    INDEX
    Explanations

    references to high school-related activities and events

    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
    1013
    +0.13
    0.4%
    1601
    +0.11
    0.3%
    964
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1601
    +0.13
    0.03
    1336
    +0.11
    0.03
    1527
    +0.11
    0.02
    Negative Logits
     Ottobre
    -0.79
     apparti
    -0.76
     sappi
    -0.74
     effe
    -0.73
     pochette
    -0.71
     affez
    -0.68
     blos
    -0.66
     parlando
    -0.66
     parlano
    -0.65
     nui
    -0.64
    POSITIVE LOGITS
     school
    0.93
     School
    0.80
    school
    0.77
     schools
    0.77
     highschool
    0.71
    School
    0.70
     шко
    0.65
     Schools
    0.64
     SCHOOL
    0.61
     students
    0.61
    Activations Density 0.076%

    No Known Activations