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. 15447
    Prev
    Next
    INDEX
    Explanations

    phrases related to hands and actions involving hands

    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
    397
    +0.13
    0.5%
    1413
    +0.12
    0.5%
    1872
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.13
    0.03
    397
    +0.12
    0.03
    1413
    +0.12
    0.03
    Negative Logits
     Gä
    -0.47
     Zwer
    -0.47
    DisplayMetrics
    -0.46
     saka
    -0.46
    怯
    -0.46
     Bele
    -0.45
     potete
    -0.45
     Mores
    -0.44
    Bele
    -0.44
    SpringBootTest
    -0.44
    POSITIVE LOGITS
     hand
    1.30
    Hand
    1.30
     Hand
    1.27
    hand
    1.25
     HAND
    1.20
    HAND
    1.14
    hands
    0.93
    Hands
    0.92
     HANDS
    0.91
     hands
    0.91
    Activations Density 0.077%

    No Known Activations