© 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. 12693
    Prev
    Next
    INDEX
    Explanations

    references to information, particularly detailed or specific information

    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
    1961
    +0.18
    0.7%
    1978
    +0.16
    0.6%
    381
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.18
    0.05
    1387
    +0.16
    0.04
    1637
    +0.14
    0.03
    Negative Logits
     nmax
    -0.67
    adecimal
    -0.63
    mbda
    -0.62
     Países
    -0.56
     strto
    -0.56
     suna
    -0.56
     Investigaciones
    -0.55
     nde
    -0.55
     kuti
    -0.55
     Crosse
    -0.54
    POSITIVE LOGITS
     disreg
    1.18
     friable
    1.13
     zirc
    1.10
     suscep
    1.09
     impractica
    1.06
     inappro
    1.05
     unlaw
    1.05
     impra
    1.04
     stratigraph
    1.00
     fidu
    1.00
    Activations Density 0.378%

    No Known Activations