© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2002
    Prev
    Next
    INDEX
    Explanations

    references to coding tools and software development practices

    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
    876
    +0.19
    0.6%
    678
    +0.13
    0.4%
    944
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.19
    0.04
    876
    +0.13
    -0.01
    1511
    +0.10
    0.01
    Negative Logits
     Cár
    -0.80
     Asunción
    -0.71
     bakteri
    -0.70
     Valentín
    -0.69
     Timoteo
    -0.69
     kemer
    -0.68
     Lázaro
    -0.68
     Belén
    -0.68
     Singapur
    -0.67
     Ávila
    -0.67
    POSITIVE LOGITS
     debugging
    0.78
     exciter
    0.78
     debugger
    0.78
     igni
    0.76
     overla
    0.73
     vespa
    0.72
     ferrari
    0.71
     dynam
    0.71
     debug
    0.71
     OPPORT
    0.69
    Activations Density 0.239%

    No Known Activations