© 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. 13462
    Prev
    Next
    INDEX
    Explanations

    keywords related to geological activities like earthquakes and volcanic eruptions

    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
    1896
    +0.17
    0.7%
    555
    +0.16
    0.7%
    1865
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.17
    0.02
    1363
    +0.16
    0.03
    555
    +0.12
    0.02
    Negative Logits
     fortsetter
    -0.58
     følger
    -0.55
     ?>/
    -0.54
     fungerer
    -0.53
     trenger
    -0.53
    кобрита
    -0.53
     finner
    -0.52
     betyr
    -0.51
    LOTTE
    -0.50
     forteller
    -0.50
    POSITIVE LOGITS
     erad
    1.22
     peppa
    1.22
     secon
    1.20
     increa
    1.18
     coq
    1.17
     hairc
    1.16
     depic
    1.16
     oreo
    1.15
     embra
    1.15
     fortn
    1.13
    Activations Density 0.125%

    No Known Activations