© 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 EvalsExportsinterp-engineNEWAPI 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. 5267
    Prev
    Next
    INDEX
    Explanations

    dialogue related to communication and understanding between characters

    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
    1419
    +0.09
    0.3%
    100
    +0.08
    0.2%
    964
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1299
    +0.09
    0.02
    100
    +0.08
    0.03
    946
    +0.08
    0.03
    Negative Logits
    Ehh
    -0.93
    Hahahahaha
    -0.91
    FTFY
    -0.89
    Hahah
    -0.89
    Mhm
    -0.88
    Ikr
    -0.84
    Lma
    -0.82
    Hahahaha
    -0.78
    Ohhhh
    -0.77
    Lmfao
    -0.76
    POSITIVE LOGITS
     WHAT
    0.71
    WHAT
    0.69
    what
    0.68
     what
    0.65
    What
    0.62
     What
    0.60
     nouveautés
    0.60
     Abstr
    0.60
     cœurs
    0.58
     xxvi
    0.57
    Activations Density 0.226%

    No Known Activations