© 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. 13447
    Prev
    Next
    INDEX
    Explanations

    references to important or significant concepts or entities

    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
    +0.17
    0.6%
    871
    +0.14
    0.5%
    1573
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    994
    +0.17
    0.04
    1573
    +0.14
    0.04
    871
    +0.12
    0.04
    Negative Logits
     tolerably
    -0.72
     withal
    -0.63
     endeavouring
    -0.59
     effectually
    -0.58
     apprehen
    -0.57
     impelled
    -0.57
     fays
    -0.55
     Condem
    -0.54
     indestru
    -0.54
     encomp
    -0.53
    POSITIVE LOGITS
    great
    1.19
     Great
    1.12
    Great
    1.12
     great
    1.08
     GREAT
    1.04
    GREAT
    0.98
    grande
    0.59
     grans
    0.58
     greatest
    0.57
     grande
    0.57
    Activations Density 0.082%

    No Known Activations