© 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. 5553
    Prev
    Next
    INDEX
    Explanations

    names of basketball players

    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
    411
    +0.18
    0.8%
    554
    +0.18
    0.8%
    889
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.18
    0.05
    227
    +0.18
    0.05
    1407
    +0.16
    0.03
    Negative Logits
     ucha
    -0.54
     dirait
    -0.53
     lili
    -0.52
     résulte
    -0.51
     kuli
    -0.50
    aurait
    -0.50
     eût
    -0.49
    Personendaten
    -0.49
     sasa
    -0.48
     kuta
    -0.48
    POSITIVE LOGITS
     Durant
    0.78
    Durant
    0.71
     shenan
    0.64
     uninten
    0.64
     Harper
    0.64
     Christie
    0.63
     joel
    0.61
    Christie
    0.57
     Joel
    0.56
    joel
    0.56
    Activations Density 0.285%

    No Known Activations