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. 1279
    Prev
    Next
    INDEX
    Explanations

    medical terms and imaging procedures related to abdominal conditions

    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
    1937
    +0.15
    0.6%
    1363
    +0.12
    0.5%
    390
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.06
    636
    +0.12
    0.05
    188
    +0.11
    0.04
    Negative Logits
    ougars
    -0.69
     anzi
    -0.63
     purtroppo
    -0.61
    haustible
    -0.61
    uckoo
    -0.60
    rítica
    -0.59
     vogliamo
    -0.58
     voleva
    -0.57
    cyjny
    -0.57
    édric
    -0.57
    POSITIVE LOGITS
     kamb
    0.76
     saar
    0.75
     c
    0.74
     konserv
    0.73
     hina
    0.69
     kasa
    0.69
     seksi
    0.69
    c
    0.67
     naer
    0.65
     Nö
    0.65
    Activations Density 0.473%

    No Known Activations