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. 1522
    Prev
    Next
    INDEX
    Explanations

    sections related to programming commands, especially in a coding context

    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
    313
    +0.17
    0.7%
    866
    +0.15
    0.6%
    1482
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.17
    0.07
    1527
    +0.15
    0.07
    1616
    +0.14
    0.07
    Negative Logits
    Vaata
    -0.65
    astéro
    -0.62
    ഊ
    -0.62
    Біографія
    -0.59
    zurück
    -0.54
    Життєпис
    -0.53
    increments
    -0.52
    ಓ
    -0.52
    SwitchCompat
    -0.51
    Nuorodos
    -0.51
    POSITIVE LOGITS
     deleter
    0.93
     SEVENTH
    0.92
     beverly
    0.83
     sven
    0.82
     maneu
    0.81
     emend
    0.81
     julie
    0.80
     Seventeenth
    0.80
     seiz
    0.79
    7
    0.78
    Activations Density 0.255%

    No Known Activations