© 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. 14319
    Prev
    Next
    INDEX
    Explanations

    descriptions of Chinese Panda coins

    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
    1842
    +0.14
    0.4%
    906
    +0.13
    0.4%
    1385
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.14
    0.06
    1192
    +0.13
    0.02
    394
    +0.11
    0.04
    Negative Logits
     bayern
    -1.04
     jaya
    -0.99
     kram
    -0.99
     saar
    -0.96
     lele
    -0.95
     uhr
    -0.95
     kado
    -0.94
     makro
    -0.93
     kasa
    -0.92
     kule
    -0.92
    POSITIVE LOGITS
     depicted
    0.71
     depiction
    0.66
     depicting
    0.63
     depicts
    0.62
     portrayed
    0.61
     depict
    0.59
     rendered
    0.57
     surrounded
    0.56
     figure
    0.54
     portraying
    0.54
    Activations Density 0.396%

    No Known Activations