© 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. 15475
    Prev
    Next
    INDEX
    Explanations

    information related to grant funding and research investments

    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
    1842
    +0.12
    0.4%
    194
    +0.09
    0.3%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.12
    0.01
    944
    +0.09
    0.02
    227
    +0.09
    0.06
    Negative Logits
    CppCodeGen
    -0.59
     Paglinawan
    -0.52
    hoedd
    -0.50
    AttributeSet
    -0.49
    ViewById
    -0.48
    getKeyCode
    -0.46
    awtextra
    -0.45
    gameserver
    -0.45
    DockStyle
    -0.45
    ContentLoaded
    -0.44
    POSITIVE LOGITS
     scientific
    0.79
     increa
    0.77
     scientists
    0.76
     snoopy
    0.76
     intersper
    0.75
     scienti
    0.74
     Scientists
    0.74
     affor
    0.73
     guarante
    0.72
     researches
    0.72
    Activations Density 0.574%

    No Known Activations