© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    mentions of weapons, specifically knives and swords

    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
    1964
    +0.13
    0.5%
    950
    +0.12
    0.4%
    1372
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1910
    +0.13
    0.03
    1363
    +0.12
    0.03
    1964
    +0.11
    0.03
    Negative Logits
     kras
    -0.85
     meis
    -0.79
     Okt
    -0.75
     boks
    -0.75
     hej
    -0.75
     ciga
    -0.74
     bej
    -0.74
     kram
    -0.73
     krab
    -0.73
     erk
    -0.72
    POSITIVE LOGITS
     blade
    1.30
     knife
    1.25
     knives
    1.15
     blades
    1.13
     Blade
    1.12
    Blade
    1.08
    blade
    1.05
     sword
    1.03
     Knife
    1.01
    knife
    1.00
    Activations Density 0.124%

    No Known Activations