© 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. 10532
    Prev
    Next
    INDEX
    Explanations

    phrases associated with legal actions or legislation

    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
    +0.39
    1.3%
    1108
    +0.14
    0.5%
    1870
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.39
    0.17
    1870
    +0.14
    0.07
    1013
    +0.12
    0.14
    Negative Logits
     estekak
    -0.64
     وتسجيلات
    -0.63
    Coucou
    -0.63
    Contactez
    -0.59
    Lindo
    -0.58
    Dobrý
    -0.57
    Cześć
    -0.56
    Ahoj
    -0.56
     Endlich
    -0.55
    Dès
    -0.53
    POSITIVE LOGITS
     bezeichneter
    0.59
    ³.
    0.57
     vost
    0.56
    ²(
    0.51
     Frenchmen
    0.51
    başı
    0.51
     ducato
    0.50
     nmax
    0.50
     poulet
    0.49
     veau
    0.49
    Activations Density 2.415%

    No Known Activations