© 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. 10590
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a part or component of something

    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
    101
    +0.10
    0.3%
    1376
    +0.10
    0.3%
    1535
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.10
    0.03
    270
    +0.10
    0.04
    1923
    +0.08
    0.03
    Negative Logits
     Câ
    -0.48
     Chá
    -0.47
     renou
    -0.45
     calda
    -0.45
     perla
    -0.44
     valla
    -0.43
     kufanya
    -0.41
     boisson
    -0.41
    Ẓ
    -0.40
    dui
    -0.40
    POSITIVE LOGITS
     portion
    1.00
    portion
    0.88
     portions
    0.84
     Portion
    0.82
    Portion
    0.71
     Portions
    0.64
     fraction
    0.64
     chunk
    0.63
    ValueStyle
    0.59
     thereof
    0.58
    Activations Density 0.144%

    No Known Activations