© 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. 3563
    Prev
    Next
    INDEX
    Explanations

    expressions conveying emotions and reactions

    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
    938
    +0.12
    0.4%
    1233
    +0.11
    0.4%
    1691
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    938
    +0.12
    0.02
    1233
    +0.11
    0.02
    1691
    +0.10
    0.02
    Negative Logits
     kosme
    -0.66
     meras
    -0.66
     antik
    -0.66
     optik
    -0.64
     kompati
    -0.63
     Okt
    -0.61
     protokol
    -0.60
     Rö
    -0.59
    Rö
    -0.59
    Debido
    -0.59
    POSITIVE LOGITS
     intersper
    0.83
     pooh
    0.74
     apprehen
    0.72
     MEAN
    0.70
     mean
    0.70
     impra
    0.67
     upvoted
    0.66
    rozum
    0.63
    MEAN
    0.62
    ⓧ
    0.62
    Activations Density 0.040%

    No Known Activations