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. 13534
    Prev
    Next
    INDEX
    Explanations

    words related to medical equipment or procedures

    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
    1910
    +0.09
    0.3%
    1018
    +0.08
    0.2%
    870
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1910
    +0.09
    0.04
    1836
    +0.08
    0.02
    870
    +0.07
    0.04
    Negative Logits
     nawr
    -0.47
     smtplib
    -0.47
    esticides
    -0.47
     BIBSYS
    -0.47
    ieb
    -0.46
    ticides
    -0.45
     ligiloj
    -0.44
    MatIconModule
    -0.44
    tivities
    -0.41
    jsxFileName
    -0.41
    POSITIVE LOGITS
    every
    0.76
     imaginable
    0.74
    Every
    0.71
     every
    0.70
     câte
    0.70
     vsak
    0.68
     začet
    0.68
     Every
    0.68
    EVERY
    0.67
     Lmao
    0.67
    Activations Density 0.286%

    No Known Activations