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. 334
    Prev
    Next
    INDEX
    Explanations

    sections of code related to memory mapping and buffer creation

    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
    1978
    +0.15
    0.5%
    1133
    +0.12
    0.4%
    776
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1614
    +0.15
    0.04
    553
    +0.12
    0.03
    406
    +0.12
    0.02
    Negative Logits
     Embaj
    -0.63
    Cuen
    -0.62
    Autoritní
    -0.61
     legte
    -0.55
     folgte
    -0.55
    حدى
    -0.54
    הע
    -0.54
    بالإ
    -0.54
    ライム
    -0.54
     schlug
    -0.52
    POSITIVE LOGITS
     grati
    1.01
     maxime
    0.97
     maro
    0.92
     labd
    0.90
     casio
    0.89
     haup
    0.88
     bordeaux
    0.88
     !...
    0.87
     intest
    0.87
     parma
    0.86
    Activations Density 0.064%

    No Known Activations