© 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. 13309
    Prev
    Next
    INDEX
    Explanations

    references to different versions of a product or concept

    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
    1044
    +0.14
    0.5%
    1059
    +0.14
    0.5%
    2011
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.14
    0.04
    1059
    +0.14
    0.04
    2011
    +0.12
    0.03
    Negative Logits
    cciale
    -0.72
     esternos
    -0.63
     autunno
    -0.62
    pendente
    -0.57
     zove
    -0.57
     reputa
    -0.56
     Aprile
    -0.56
    Referencoj
    -0.56
     fuo
    -0.55
    anskje
    -0.55
    POSITIVE LOGITS
     version
    1.28
    version
    1.16
     versions
    1.14
     Version
    1.12
    Version
    1.10
     VERSION
    1.08
     Versions
    0.96
    VERSION
    0.96
    versions
    0.91
    版本
    0.88
    Activations Density 0.091%

    No Known Activations