© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7488
    Prev
    Next
    INDEX
    Explanations

    references to mass surveillance, government control, and security issues

    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
    667
    +0.13
    0.4%
    674
    +0.12
    0.4%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.13
    0.04
    1351
    +0.12
    0.03
    1059
    +0.10
    0.03
    Negative Logits
    alnız
    -0.60
     déclarations
    -0.58
    ardı
    -0.56
    InputTagHelper
    -0.55
    vstack
    -0.54
     procédures
    -0.54
     écrans
    -0.54
     investissements
    -0.54
     créations
    -0.53
    şekkür
    -0.53
    POSITIVE LOGITS
     valencia
    0.77
     pican
    0.69
     tulum
    0.62
     vernac
    0.61
     palab
    0.60
     haup
    0.59
     schi
    0.58
    vailable
    0.58
     riu
    0.57
     fere
    0.57
    Activations Density 0.152%

    No Known Activations