© 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. 16185
    Prev
    Next
    INDEX
    Explanations

    code snippets related to defining classes and methods in a programming context

    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
    453
    +0.13
    0.4%
    1177
    +0.13
    0.4%
    1108
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.13
    0.04
    1061
    +0.13
    0.01
    1098
    +0.10
    0.02
    Negative Logits
    contentLoaded
    -0.76
     unknownFields
    -0.69
    RegressionTest
    -0.67
    abestanden
    -0.65
    setViewportView
    -0.60
     архивлан
    -0.58
    StoryboardSegue
    -0.57
     дописавши
    -0.56
     getItemCount
    -0.55
    StructEnd
    -0.53
    POSITIVE LOGITS
     effe
    0.96
     dises
    0.95
     fta
    0.94
     noss
    0.94
     vns
    0.92
     mef
    0.89
     ftu
    0.88
     fei
    0.87
     peculi
    0.87
     increa
    0.86
    Activations Density 0.283%

    No Known Activations