© 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. 6337
    Prev
    Next
    INDEX
    Explanations

    references to specific publications such as papers, articles, and reports

    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
    872
    +0.13
    0.4%
    1150
    +0.11
    0.3%
    776
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1780
    +0.13
    0.03
    166
    +0.11
    0.04
    838
    +0.09
    0.04
    Negative Logits
     bordeaux
    -1.49
     eiffel
    -1.42
     matel
    -1.40
     ibiza
    -1.37
     swarovski
    -1.37
     peppa
    -1.36
     murano
    -1.34
     pican
    -1.33
     nutella
    -1.33
     oreo
    -1.33
    POSITIVE LOGITS
     contains
    0.82
     describes
    0.79
     focuses
    0.78
     titled
    0.76
     detailing
    0.75
     depicts
    0.75
     focused
    0.74
     contain
    0.73
     suggests
    0.73
     discusses
    0.71
    Activations Density 0.416%

    No Known Activations