© 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. 6115
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantity, age, calibers, and injuries

    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
    1042
    +0.14
    0.4%
    1965
    +0.10
    0.3%
    468
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.14
    0.05
    1960
    +0.10
    0.03
    2005
    +0.08
    0.03
    Negative Logits
     BIBSYS
    -0.80
     lancia
    -0.78
     ridu
    -0.72
     confé
    -0.71
     Lég
    -0.68
     mâle
    -0.68
     perpétu
    -0.67
     cammin
    -0.66
     Dép
    -0.66
     CiNii
    -0.66
    POSITIVE LOGITS
     nature
    0.63
    Noice
    0.56
    Hahah
    0.53
    Lmfao
    0.53
     ujedno
    0.52
     liberality
    0.52
     proximity
    0.51
     requirement
    0.50
     similarity
    0.50
    Tbh
    0.50
    Activations Density 0.492%

    No Known Activations