© 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. 11064
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates, times, and images

    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
    16
    +0.14
    0.4%
    1978
    +0.12
    0.3%
    605
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1471
    +0.14
    0.04
    267
    +0.12
    0.03
    453
    +0.12
    0.04
    Negative Logits
     utop
    -1.35
     rente
    -1.32
     furg
    -1.27
     revisor
    -1.27
     atle
    -1.26
     sement
    -1.26
     impon
    -1.25
     monaster
    -1.24
     marte
    -1.24
     fras
    -1.24
    POSITIVE LOGITS
     unspeak
    2.24
     intersper
    2.21
     impra
    2.19
     depic
    2.13
     encomp
    2.10
     shenan
    2.09
     reluct
    2.09
     disagre
    2.01
     apprehen
    1.90
     unlaw
    1.85
    Activations Density 0.199%

    No Known Activations