© 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. 2385
    Prev
    Next
    INDEX
    Explanations

    terms related to violent actions and their consequences, particularly in historical or political contexts

    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
    604
    +0.10
    0.3%
    906
    +0.10
    0.3%
    792
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.10
    0.08
    946
    +0.10
    0.06
    509
    +0.09
    0.06
    Negative Logits
     lele
    -1.01
     haup
    -0.95
     sentra
    -0.89
     maksi
    -0.88
     bandung
    -0.88
     hina
    -0.88
     jaya
    -0.88
     manuten
    -0.88
     ciment
    -0.87
     istan
    -0.86
    POSITIVE LOGITS
     afterwards
    0.70
     afterward
    0.64
     recovered
    0.63
     recover
    0.63
     injured
    0.62
     recovery
    0.61
     bleeding
    0.60
     recovering
    0.59
     thereafter
    0.59
    Afterwards
    0.58
    Activations Density 0.512%

    No Known Activations