© 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. 13782
    Prev
    Next
    INDEX
    Explanations

    descriptions of a specific event involving an armed confrontation and a police standoff

    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
    946
    +0.11
    0.3%
    453
    +0.11
    0.3%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.07
    658
    +0.11
    0.05
    736
    +0.10
    0.05
    Negative Logits
     tricot
    -0.99
     [''
    -0.99
     fatis
    -0.97
     applau
    -0.97
     doman
    -0.95
     embodi
    -0.95
     ciment
    -0.94
     germain
    -0.93
     rhum
    -0.92
     parf
    -0.92
    POSITIVE LOGITS
     eventually
    0.50
     police
    0.50
     shootout
    0.49
    пенно
    0.48
     later
    0.47
     ensued
    0.47
     opened
    0.47
     officers
    0.46
     lebte
    0.46
     finally
    0.46
    Activations Density 0.295%

    No Known Activations