© 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. 7260
    Prev
    Next
    INDEX
    Explanations

    written sequences like repetitive forum posts

    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
    453
    +0.22
    0.6%
    1728
    +0.08
    0.2%
    964
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.22
    0.04
    1417
    +0.08
    0.03
    1434
    +0.06
    0.03
    Negative Logits
     Mmm
    -0.83
     Wtf
    -0.78
    Fuckin
    -0.77
    FTFY
    -0.76
     Lmao
    -0.75
     unspeak
    -0.74
    Cringe
    -0.74
     Ahh
    -0.73
     Considerable
    -0.73
    Derp
    -0.71
    POSITIVE LOGITS
     PLWABN
    0.83
     liev
    0.79
     frans
    0.78
     parati
    0.78
     zucca
    0.77
     affez
    0.76
     CreateTagHelper
    0.74
     morire
    0.72
     SUDOC
    0.72
     roh
    0.71
    Activations Density 0.130%

    No Known Activations