© 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. 13090
    Prev
    Next
    INDEX
    Explanations

    emotional and evocative language, particularly related to deep feelings

    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
    1241
    +0.10
    0.3%
    519
    +0.08
    0.2%
    1356
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1241
    +0.10
    0.05
    697
    +0.08
    0.07
    1823
    +0.08
    0.03
    Negative Logits
     javier
    -0.85
     josé
    -0.84
     oliveira
    -0.80
     felipe
    -0.79
     jorge
    -0.77
     Dica
    -0.75
     elek
    -0.75
     roberto
    -0.74
     sergio
    -0.74
     necessarie
    -0.74
    POSITIVE LOGITS
     emotional
    0.74
     emotion
    0.69
     emotions
    0.68
     heartfelt
    0.68
     poignant
    0.66
     heartbreaking
    0.62
     emotionally
    0.61
    emotional
    0.58
     compassion
    0.57
     empathy
    0.56
    Activations Density 0.874%

    No Known Activations