© 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. 1954
    Prev
    Next
    INDEX
    Explanations

    details related to violent and tragic events, particularly involving physical harm or injury

    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
    569
    +0.11
    0.3%
    1385
    +0.10
    0.3%
    438
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.11
    0.06
    569
    +0.10
    0.05
    1142
    +0.09
    0.03
    Negative Logits
     praktik
    -1.21
     kompati
    -1.17
     tramont
    -1.15
     robus
    -1.14
     Settembre
    -1.13
     ordina
    -1.12
     alkoh
    -1.12
     kosme
    -1.09
     Ottobre
    -1.08
     chande
    -1.08
    POSITIVE LOGITS
     cut
    0.75
     cuts
    0.73
     cutting
    0.73
     pieces
    0.68
    cutting
    0.64
    cut
    0.63
     slice
    0.60
     slices
    0.60
     fragments
    0.59
    cuts
    0.59
    Activations Density 0.266%

    No Known Activations