© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2477
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to pharmaceuticals and chemistry

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    169
    +0.08
    0.2%
    1562
    +0.07
    0.2%
    650
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    774
    +0.08
    0.02
    644
    +0.07
    0.02
    1916
    +0.07
    0.02
    Negative Logits
    Посилання
    -0.55
    ⓧ
    -0.54
    webElementXpaths
    -0.53
    DataAnnotations
    -0.53
    EndProject
    -0.52
    קישורים
    -0.52
    htbp
    -0.52
    ModelSerializer
    -0.51
    getResultList
    -0.50
    Portály
    -0.50
    POSITIVE LOGITS
     compound
    3.13
     Compound
    3.10
    compound
    2.94
    Compound
    2.75
     compounds
    2.56
     Compounds
    2.49
     COMPOUND
    2.46
     compounding
    2.01
     compounded
    1.92
     COMPOUNDS
    1.59
    Activations Density 0.192%

    No Known Activations