© 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 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. 14805
    Prev
    Next
    INDEX
    Explanations

    technical information related to a military operation

    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
    946
    +0.19
    0.6%
    344
    +0.18
    0.6%
    509
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.19
    0.07
    509
    +0.18
    0.06
    599
    +0.13
    0.05
    Negative Logits
     Chambres
    -0.62
     Chinois
    -0.62
     veau
    -0.58
     susun
    -0.58
     potes
    -0.57
     ivi
    -0.57
     Mère
    -0.56
     harap
    -0.56
     maniere
    -0.56
     lende
    -0.55
    POSITIVE LOGITS
     relayed
    0.79
     disreg
    0.66
     unlaw
    0.63
     Communicating
    0.61
     notifying
    0.61
     alerting
    0.60
     impractica
    0.58
     remot
    0.58
     transmitting
    0.57
     reporting
    0.57
    Activations Density 0.602%

    No Known Activations