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. 15821
    Prev
    Next
    INDEX
    Explanations

    technical code syntax patterns and programming concepts

    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
    764
    +0.07
    0.2%
    227
    +0.07
    0.2%
    1799
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1799
    +0.07
    0.02
    527
    +0.07
    0.03
    474
    +0.07
    0.02
    Negative Logits
     makro
    -0.88
     silikon
    -0.80
     lele
    -0.77
     akut
    -0.77
     panik
    -0.75
     Kategor
    -0.74
     alkoh
    -0.73
     katal
    -0.72
     maksi
    -0.71
     mikrofon
    -0.70
    POSITIVE LOGITS
     later
    0.82
     tomorrow
    0.72
     senere
    0.70
     LATER
    0.69
     pylab
    0.65
     disreg
    0.62
    Later
    0.61
    later
    0.60
     tupperware
    0.59
     Later
    0.58
    Activations Density 0.206%

    No Known Activations