© 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. 10677
    Prev
    Next
    INDEX
    Explanations

    information regarding police activities and criminal incidents

    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
    764
    +0.20
    0.6%
    198
    +0.17
    0.5%
    1177
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.20
    0.04
    198
    +0.17
    0.04
    1920
    +0.14
    0.04
    Negative Logits
    InitStruct
    -0.53
     ॥
    -0.51
    _));
    -0.49
     ?>/
    -0.49
     propOrder
    -0.48
     المعيارى
    -0.46
    ecimento
    -0.45
     кул
    -0.45
    ´)
    -0.45
    tadır
    -0.45
    POSITIVE LOGITS
     aen
    1.11
     fta
    1.09
     thut
    1.06
     fte
    1.06
     Juf
    1.04
     emphat
    1.01
     Minang
    1.00
     wherea
    1.00
     oun
    1.00
     illi
    0.99
    Activations Density 0.224%

    No Known Activations