© 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. 3947
    Prev
    Next
    INDEX
    Explanations

    mentions of challenging or dangerous situations, especially related to conflict or survival

    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
    +0.12
    0.3%
    1013
    +0.09
    0.3%
    297
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1171
    +0.12
    0.04
    736
    +0.09
    0.05
    595
    +0.09
    0.03
    Negative Logits
     unsus
    -0.52
     mischie
    -0.52
     miscon
    -0.48
     intrigu
    -0.46
     subtil
    -0.46
    RTN
    -0.45
     pistolet
    -0.44
     calum
    -0.44
     pooh
    -0.43
    Guilty
    -0.43
    POSITIVE LOGITS
     fatte
    0.70
    Lmfao
    0.69
     fondamentali
    0.65
     nutella
    0.62
    €/
    0.60
     scoper
    0.60
     😭😭
    0.58
    Ikr
    0.57
     jeste
    0.57
    seigneur
    0.56
    Activations Density 0.441%

    No Known Activations