© 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. 13263
    Prev
    Next
    INDEX
    Explanations

    recommendations or strategies related to teaching or learning mathematics

    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
    1331
    +0.12
    0.4%
    486
    +0.11
    0.4%
    899
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    899
    +0.12
    0.02
    1331
    +0.11
    0.02
    683
    +0.10
    0.02
    Negative Logits
     revan
    -0.80
     Souha
    -0.80
     Strukt
    -0.70
     viciss
    -0.70
     benevol
    -0.68
     Osp
    -0.67
     Bén
    -0.67
     Juf
    -0.67
     socie
    -0.67
     pessi
    -0.67
    POSITIVE LOGITS
     emphasis
    1.02
     emphasize
    0.98
     emphasized
    0.94
     emphasizing
    0.89
    emphas
    0.85
     emphasizes
    0.84
     emphasise
    0.82
     emphasised
    0.79
     Emphasis
    0.75
    emphasis
    0.75
    Activations Density 0.075%

    No Known Activations