© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12002
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical terms and equations

    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
    184
    +0.08
    0.2%
    1719
    +0.07
    0.2%
    1075
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.08
    0.01
    310
    +0.07
    0.02
    343
    +0.07
    0.04
    Negative Logits
     Méri
    -0.66
     Valentín
    -0.57
    Kanpo
    -0.56
     borgo
    -0.55
    vantages
    -0.54
     doña
    -0.53
     Chwiliwch
    -0.53
     îna
    -0.52
     Arque
    -0.51
     autunno
    -0.51
    POSITIVE LOGITS
     quitted
    0.66
     emphat
    0.66
     wien
    0.65
     seiz
    0.65
     thut
    0.65
     gis
    0.64
     Quod
    0.63
     desir
    0.63
     caprice
    0.63
     coö
    0.62
    Activations Density 0.495%

    No Known Activations