© 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. 3640
    Prev
    Next
    INDEX
    Explanations

    action verbs related to demonstrating or presenting something

    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
    1482
    +0.14
    0.5%
    814
    +0.12
    0.5%
    869
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    869
    +0.14
    0.06
    1482
    +0.12
    0.05
    966
    +0.12
    0.05
    Negative Logits
     Yugos
    -0.54
     Danzig
    -0.53
     Eberhard
    -0.51
     Cartagena
    -0.51
     languid
    -0.50
     Emi
    -0.50
     Alicante
    -0.50
     Piedra
    -0.50
     mercurial
    -0.49
     Corinne
    -0.49
    POSITIVE LOGITS
     show
    1.28
    show
    1.26
     SHOW
    1.22
    shows
    1.20
     SHOWS
    1.19
     shows
    1.15
    SHOW
    1.13
    Shows
    1.13
     Show
    1.12
    Show
    1.12
    Activations Density 0.132%

    No Known Activations