© 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. 13258
    Prev
    Next
    INDEX
    Explanations

    author names and journal publication 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
    1343
    +0.18
    0.5%
    1699
    +0.14
    0.4%
    1741
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.18
    0.04
    323
    +0.14
    0.03
    1343
    +0.13
    0.03
    Negative Logits
    adalajara
    -0.78
    ">...
    -0.69
    Quiénes
    -0.69
     soggior
    -0.68
     interessanti
    -0.67
    ayaquil
    -0.67
     succede
    -0.66
     scattata
    -0.66
     purtroppo
    -0.66
    Economía
    -0.65
    POSITIVE LOGITS
     Deviant
    0.94
     &.
    0.89
     Illus
    0.84
     Addon
    0.84
     noyau
    0.83
     [?]
    0.79
     ^^^
    0.78
     mécanisme
    0.77
     maintien
    0.76
     Hd
    0.74
    Activations Density 0.052%

    No Known Activations