© 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. 13821
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing things as good, great, or beautiful

    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
    994
    +0.14
    0.5%
    1839
    +0.11
    0.4%
    605
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    994
    +0.14
    0.04
    1839
    +0.11
    0.04
    214
    +0.10
    0.03
    Negative Logits
     indestru
    -1.04
     🤣🤣
    -0.99
     lavorato
    -0.97
     ricardo
    -0.96
     alberto
    -0.96
     ?...
    -0.96
     sergio
    -0.95
     jorge
    -0.93
     scoperto
    -0.92
    FTFY
    -0.91
    POSITIVE LOGITS
    <bos>
    0.97
     great
    0.94
    great
    0.86
     Great
    0.85
    Great
    0.82
     GREAT
    0.74
     excellent
    0.64
    GREAT
    0.63
     fantastic
    0.63
     good
    0.61
    Activations Density 0.137%

    No Known Activations