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. 352
    Prev
    Next
    INDEX
    Explanations

    specific statements or claims presented as facts

    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
    1965
    +0.12
    0.4%
    184
    +0.08
    0.3%
    124
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.12
    0.06
    1287
    +0.08
    0.04
    1839
    +0.07
    0.05
    Negative Logits
     teras
    -0.77
     Keny
    -0.75
     bambu
    -0.69
     Kese
    -0.66
     istan
    -0.65
     valla
    -0.64
     migli
    -0.64
     masaj
    -0.63
     Juf
    -0.63
     sò
    -0.62
    POSITIVE LOGITS
    Bardzo
    0.71
    Może
    0.68
    Prí
    0.66
    Dzięki
    0.65
    Și
    0.62
    Asimismo
    0.61
    Dziękuję
    0.61
    Kiedy
    0.60
    Dlaczego
    0.60
    Gdzie
    0.59
    Activations Density 0.304%

    No Known Activations