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. 15749
    Prev
    Next
    INDEX
    Explanations

    global locations and events

    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
    2034
    +0.14
    0.4%
    1296
    +0.11
    0.3%
    1438
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.14
    0.04
    1296
    +0.11
    0.04
    791
    +0.09
    0.03
    Negative Logits
     initComponents
    -0.55
     Anm
    -0.47
    ἐ
    -0.47
    bonsoir
    -0.47
    Sö
    -0.46
    Alte
    -0.46
     luxem
    -0.46
     bergen
    -0.45
     stiller
    -0.45
    Schweizer
    -0.45
    POSITIVE LOGITS
    world
    0.68
     unwarran
    0.66
    World
    0.66
    WORLD
    0.65
     ecru
    0.65
     Normdatei
    0.64
     World
    0.64
     snapback
    0.64
     WORLD
    0.64
     sceptre
    0.63
    Activations Density 0.097%

    No Known Activations