© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13380
    Prev
    Next
    INDEX
    Explanations

    phrases indicating support, preparedness, and liking something

    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
    198
    +0.14
    0.4%
    1314
    +0.09
    0.3%
    678
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.06
    92
    +0.09
    0.05
    100
    +0.07
    0.04
    Negative Logits
     unspeak
    -0.90
     unwarran
    -0.89
     disagre
    -0.89
     reluct
    -0.86
     impra
    -0.86
     shenan
    -0.84
     increa
    -0.83
     pamph
    -0.83
     affor
    -0.81
     inconce
    -0.81
    POSITIVE LOGITS
     things
    0.60
    tagPool
    0.58
     grans
    0.57
     masaj
    0.57
     disambiguazione
    0.56
    homonymie
    0.54
     anything
    0.53
     Roskov
    0.53
     excur
    0.52
    ностран
    0.51
    Activations Density 0.762%

    No Known Activations