© 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. 16229
    Prev
    Next
    INDEX
    Explanations

    word stems related to the field of forensics

    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
    298
    +0.12
    0.5%
    156
    +0.12
    0.5%
    596
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.12
    0.03
    597
    +0.12
    0.02
    406
    +0.12
    0.01
    Negative Logits
    Polic
    -0.56
    splitlines
    -0.49
    Bibliograf
    -0.44
    Autoritní
    -0.44
     Oswald
    -0.43
     Dutch
    -0.43
     Hubert
    -0.43
    glBind
    -0.42
     Irwin
    -0.42
     Mier
    -0.42
    POSITIVE LOGITS
    Fore
    1.30
     Fore
    1.28
     fore
    1.22
     FORE
    1.20
    fore
    1.18
     bandung
    0.93
     susun
    0.90
     jawa
    0.90
    FORE
    0.89
     affez
    0.85
    Activations Density 0.106%

    No Known Activations