© 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. 2394
    Prev
    Next
    INDEX
    Explanations

    events and actions related to politics, conflicts, and ransom demands

    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
    198
    +0.10
    0.3%
    946
    +0.10
    0.3%
    604
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.10
    0.04
    198
    +0.10
    0.04
    199
    +0.08
    0.01
    Negative Logits
     wien
    -1.08
     aen
    -0.94
     gmbh
    -0.93
     ftu
    -0.93
     waer
    -0.91
     bordeaux
    -0.90
     thut
    -0.89
     fluo
    -0.89
     coq
    -0.88
     ugg
    -0.88
    POSITIVE LOGITS
     responsible
    0.65
     responsibility
    0.60
     involvement
    0.54
     involved
    0.50
     esternos
    0.50
     organized
    0.49
    Galería
    0.48
     hired
    0.48
     perpetrators
    0.48
    ншни
    0.48
    Activations Density 0.440%

    No Known Activations