© 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. 6997
    Prev
    Next
    INDEX
    Explanations

    strong statements or quotes made by individuals in public discussions or debates

    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
    878
    +0.10
    0.3%
    1150
    +0.10
    0.3%
    1637
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    878
    +0.10
    0.08
    32
    +0.10
    0.07
    1068
    +0.09
    0.08
    Negative Logits
    <?
    -0.73
     eût
    -0.70
     voulait
    -0.67
    /*
    -0.67
    Lmfao
    -0.65
     répondit
    -0.65
    Ikr
    -0.64
    Bisous
    -0.64
    
    -0.63
     robus
    -0.63
    POSITIVE LOGITS
     said
    0.71
     Said
    0.66
     Mahomet
    0.65
     saying
    0.64
     pooh
    0.61
     unspeak
    0.60
     sarcas
    0.60
     says
    0.59
     say
    0.58
     faggot
    0.58
    Activations Density 0.290%

    No Known Activations