© 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. 4796
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and actions

    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
    1352
    +0.09
    0.2%
    1177
    +0.08
    0.2%
    77
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1477
    +0.09
    0.07
    1607
    +0.08
    0.04
    77
    +0.07
    0.05
    Negative Logits
     curé
    -0.71
     Mémoires
    -0.63
     parf
    -0.62
     bourg
    -0.61
     potes
    -0.59
     Romains
    -0.59
     Sénat
    -0.59
     violon
    -0.58
     commandement
    -0.57
     fuo
    -0.57
    POSITIVE LOGITS
     McLaugh
    0.61
     mahd
    0.56
     Keny
    0.55
     mList
    0.53
     stratigraph
    0.52
     reconsideration
    0.52
     Momb
    0.51
     Pantai
    0.50
     EEU
    0.50
     purtroppo
    0.48
    Activations Density 0.467%

    No Known Activations