© 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. 14928
    Prev
    Next
    INDEX
    Explanations

    references to a specific news network

    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
    2004
    +0.17
    0.7%
    501
    +0.15
    0.6%
    650
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.17
    0.03
    2004
    +0.15
    0.03
    501
    +0.14
    0.03
    Negative Logits
    queryInterface
    -0.67
    Autoritní
    -0.64
     autorytatywna
    -0.59
    VolleyError
    -0.59
    asteroide
    -0.57
     pinulongan
    -0.56
    CheckedChanged
    -0.56
    SequentialGroup
    -0.55
    Parcelize
    -0.54
    AnchorStyles
    -0.54
    POSITIVE LOGITS
     Fox
    1.45
    Fox
    1.42
     fox
    1.30
    fox
    1.24
     FOX
    1.22
     foxes
    1.04
     Foxes
    1.04
    FOX
    1.03
     Khart
    0.99
     Minang
    0.95
    Activations Density 0.078%

    No Known Activations