© 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 EvalsExportsinterp-engineNEWAPI 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. 16211
    Prev
    Next
    INDEX
    Explanations

    references to achievements or top rankings in different categories

    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
    1507
    +0.14
    0.5%
    197
    +0.13
    0.5%
    75
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.14
    0.06
    1507
    +0.13
    0.05
    623
    +0.12
    0.05
    Negative Logits
     Marín
    -0.61
     Domínguez
    -0.60
     rodriguez
    -0.52
      (
    -0.51
     juventus
    -0.50
     pymysql
    -0.49
    więcej
    -0.49
     Azevedo
    -0.49
    Fprintf
    -0.49
     Câ
    -0.49
    POSITIVE LOGITS
    best
    1.15
     Best
    1.13
     best
    1.12
     BEST
    1.08
    Best
    1.07
    BEST
    1.02
    worst
    0.78
     beste
    0.72
     worst
    0.69
     Worst
    0.67
    Activations Density 0.116%

    No Known Activations