© 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. 6150
    Prev
    Next
    INDEX
    Explanations

    software-related terms and identifiers, possibly related to tasks and computing functionalities

    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
    1510
    +0.13
    0.4%
    1343
    +0.13
    0.4%
    1150
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.13
    0.03
    1473
    +0.13
    0.02
    1343
    +0.12
    0.04
    Negative Logits
    Več
    -0.85
    Dlaczego
    -0.68
    Prí
    -0.65
    Czym
    -0.65
    Przyp
    -0.63
    sergio
    -0.62
    غيرة
    -0.62
    Wię
    -0.61
     amongst
    -0.61
    bardziej
    -0.61
    POSITIVE LOGITS
     meis
    1.29
     dises
    1.29
     illi
    1.23
     meras
    1.22
     saar
    1.22
     prodi
    1.21
     grati
    1.21
     erec
    1.21
     sii
    1.21
     !...
    1.21
    Activations Density 0.126%

    No Known Activations