© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2494
    Prev
    Next
    INDEX
    Explanations

    phrases related to debate or argumentation, specifically statements of disagreement or counterpoints

    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
    1892
    +0.13
    0.4%
    25
    +0.12
    0.4%
    1993
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1993
    +0.13
    0.07
    1166
    +0.12
    0.07
    1325
    +0.11
    0.04
    Negative Logits
    Personensuche
    -0.77
    Tại
    -0.61
    Ảnh
    -0.61
     treball
    -0.61
    Thời
    -0.60
    RegressionTest
    -0.58
    Và
    -0.57
     bunda
    -0.57
    Chúng
    -0.56
     getNome
    -0.56
    POSITIVE LOGITS
     fta
    1.20
     wherea
    1.06
     thut
    1.05
     fto
    1.04
     Augu
    1.01
     fortn
    0.99
     laft
    0.98
     stickied
    0.98
     tew
    0.98
     gaily
    0.97
    Activations Density 0.520%

    No Known Activations