© 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 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. 10789
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning peculiar or unusual aspects, especially related to locations or people's actions

    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
    468
    +0.12
    0.4%
    776
    +0.10
    0.4%
    1222
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.12
    0.04
    1077
    +0.10
    0.04
    1935
    +0.10
    0.03
    Negative Logits
     kooper
    -0.48
    Enumerated
    -0.48
    ToolStripButton
    -0.48
     bezw
    -0.47
    AllowUser
    -0.45
    DataBind
    -0.45
     négatif
    -0.45
    -------
    -0.45
    ximadamente
    -0.44
    Prat
    -0.44
    POSITIVE LOGITS
     odd
    1.04
     Odd
    0.92
     weird
    0.91
     strangest
    0.90
     strange
    0.90
    Odd
    0.88
     shewn
    0.83
    odd
    0.83
     Weird
    0.82
    strange
    0.82
    Activations Density 0.128%

    No Known Activations