© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11648
    Prev
    Next
    INDEX
    Explanations

    mentions of violent actions or situations

    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
    1177
    +0.11
    0.3%
    1842
    +0.10
    0.3%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.11
    0.06
    946
    +0.10
    0.05
    189
    +0.10
    0.04
    Negative Logits
     fers
    -1.00
     stik
    -0.80
     tille
    -0.78
     stiller
    -0.78
     asics
    -0.76
     tyn
    -0.76
     sels
    -0.75
     ananas
    -0.74
     drap
    -0.74
     aquare
    -0.73
    POSITIVE LOGITS
     Darío
    0.82
     Mejía
    0.78
     Marín
    0.77
     Áng
    0.72
     Méndez
    0.69
     Domínguez
    0.67
     innocent
    0.65
     Cárdenas
    0.60
     Núñez
    0.59
     Bartholo
    0.58
    Activations Density 0.365%

    No Known Activations