© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    texts related to social or political events, such as news reporting or opinions

    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
    1535
    +0.13
    0.4%
    776
    +0.12
    0.4%
    897
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.13
    0.05
    220
    +0.12
    0.05
    666
    +0.10
    0.03
    Negative Logits
    <bos>
    -0.65
    Dichloroethene
    -0.47
    HasMaxLength
    -0.46
    ֶה
    -0.44
    
    -0.43
    sunami
    -0.43
     dreapta
    -0.42
     liten
    -0.42
     getUsers
    -0.42
     Главная
    -0.42
    POSITIVE LOGITS
     vito
    1.03
     sappi
    0.95
     ritard
    0.95
     canel
    0.93
     revan
    0.92
     pican
    0.91
     milano
    0.90
     churrasco
    0.90
     tortas
    0.90
     imposs
    0.88
    Activations Density 0.258%

    No Known Activations