Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1687
    Prev
    Next
    INDEX
    Explanations

    entities related to investigations and examinations, such as investigators, researchers, and experts

    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
    513
    +0.11
    0.4%
    1865
    +0.10
    0.3%
    889
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1865
    +0.11
    0.04
    484
    +0.10
    0.04
    513
    +0.09
    0.04
    Negative Logits
     imprend
    -0.56
     pères
    -0.55
     Pagina
    -0.53
     ambassade
    -0.48
     anivers
    -0.48
    Volumen
    -0.47
    zette
    -0.47
     electrica
    -0.46
     prêtres
    -0.46
    serviceName
    -0.46
    POSITIVE LOGITS
     alha
    0.65
     naer
    0.58
     apprehen
    0.57
     saad
    0.57
     withal
    0.56
     którzy
    0.56
    pecified
    0.56
     kelle
    0.55
    investors
    0.55
     negotiators
    0.55
    Activations Density 0.255%

    No Known Activations