© 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. 11154
    Prev
    Next
    INDEX
    Explanations

    information related to graphic quality and technical specifications in a visual medium

    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
    690
    +0.12
    0.4%
    2034
    +0.10
    0.3%
    1150
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.12
    0.02
    1418
    +0.10
    0.04
    615
    +0.10
    0.03
    Negative Logits
     „,
    -1.21
     aen
    -1.19
     kram
    -1.17
     ivi
    -1.17
     oun
    -1.08
     fta
    -1.04
     socie
    -1.03
     NOO
    -1.01
     lemp
    -1.01
     effe
    -1.00
    POSITIVE LOGITS
    blouse
    0.66
     câte
    0.62
    visející
    0.60
     tæt
    0.58
    lcccccc
    0.58
     gawas
    0.58
    raught
    0.57
     waistcoat
    0.56
     pettico
    0.56
    ATEGY
    0.56
    Activations Density 0.425%

    No Known Activations