© 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 EvalsExportsinterp-engineNEWAPI 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. 4904
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices like cellphones

    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
    946
    +0.13
    0.4%
    190
    +0.12
    0.4%
    1150
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.13
    0.04
    190
    +0.12
    0.03
    724
    +0.11
    0.03
    Negative Logits
     fta
    -1.09
     increa
    -1.08
     encomp
    -1.06
     guarante
    -1.04
     ftu
    -1.04
     volunte
    -1.01
     reluct
    -1.01
     vhs
    -1.00
     secon
    -1.00
     fua
    -0.98
    POSITIVE LOGITS
     device
    0.59
     laptop
    0.58
     phones
    0.56
    estacks
    0.55
     computer
    0.55
    💻
    0.55
     devices
    0.54
     phone
    0.53
     computers
    0.53
     mobile
    0.52
    Activations Density 0.324%

    No Known Activations