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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1023
    Prev
    Next
    INDEX
    Explanations

    adverbs describing actions or emotions

    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
    1177
    +0.15
    0.5%
    1870
    +0.15
    0.5%
    1415
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.15
    0.05
    1919
    +0.15
    0.07
    1490
    +0.11
    0.07
    Negative Logits
     véhic
    -0.96
     gouver
    -0.90
     cristina
    -0.89
     réal
    -0.86
     alberto
    -0.86
     ricardo
    -0.86
     javier
    -0.83
     intersper
    -0.83
     obé
    -0.81
     nicolas
    -0.80
    POSITIVE LOGITS
    asteroide
    0.82
     vairāk
    0.73
     BoxFit
    0.73
    <bos>
    0.72
     izvē
    0.70
    astéro
    0.69
    ICALLY
    0.68
    toHaveBeen
    0.62
    lably
    0.61
    ранее
    0.61
    Activations Density 0.318%

    No Known Activations