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. 1649
    Prev
    Next
    INDEX
    Explanations

    functions or methods related to programming

    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
    1343
    +0.13
    0.4%
    537
    +0.09
    0.3%
    1981
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.13
    0.05
    609
    +0.09
    0.04
    382
    +0.09
    0.04
    Negative Logits
    MfG
    -0.55
     snippetHide
    -0.55
     do
    -0.48
    Gruß
    -0.47
    Хоро
    -0.45
    Grüße
    -0.44
    Nein
    -0.44
    Ұ
    -0.43
     Do
    -0.43
    Кара
    -0.43
    POSITIVE LOGITS
     fta
    1.12
     eduardo
    1.11
     peugeot
    1.08
     ftu
    1.07
     javier
    1.07
     juft
    1.07
     guatemala
    1.05
     vns
    1.04
     siena
    1.04
     fep
    1.03
    Activations Density 0.159%

    No Known Activations