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. 332
    Prev
    Next
    INDEX
    Explanations

    quotes or reported statements from individuals

    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
    +0.16
    0.5%
    1253
    +0.15
    0.5%
    478
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.16
    0.17
    19
    +0.15
    0.17
    1533
    +0.13
    0.10
    Negative Logits
    Lmfao
    -0.94
    Gdzie
    -0.88
    Zapraszamy
    -0.85
    Może
    -0.85
    Czym
    -0.84
    Wię
    -0.81
    Díky
    -0.81
    Cześć
    -0.81
    Kiedy
    -0.80
    nasel
    -0.80
    POSITIVE LOGITS
     Halen
    0.67
    unno
    0.67
    rizona
    0.64
    (%)
    0.64
     raso
    0.63
     torba
    0.62
    ventus
    0.62
     bronzo
    0.62
    Flammable
    0.62
    mavi
    0.61
    Activations Density 1.474%

    No Known Activations