Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14748
    Prev
    Next
    INDEX
    Explanations

    mentions of military invasions, especially focusing on the consequences and reactions related to different conflicts

    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
    2004
    +0.13
    0.4%
    1763
    +0.11
    0.4%
    1325
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.13
    0.03
    2004
    +0.11
    0.03
    765
    +0.11
    0.02
    Negative Logits
     manik
    -0.64
     affez
    -0.62
     verba
    -0.60
     huma
    -0.59
     shur
    -0.59
     bals
    -0.59
     pira
    -0.57
     scoper
    -0.57
     peculi
    -0.57
     eam
    -0.57
    POSITIVE LOGITS
     invasion
    1.20
     Invasion
    1.04
     invade
    1.04
    Invasion
    0.98
     invaded
    0.97
     invasions
    0.95
    invasion
    0.95
     invading
    0.92
     invasive
    0.85
    invasive
    0.81
    Activations Density 0.104%

    No Known Activations