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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7863
    Prev
    Next
    INDEX
    Explanations

    references to public education and related resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.38
    1.4%
    1013
    +0.11
    0.4%
    509
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1336
    +0.38
    0.07
    1533
    +0.11
    0.03
    527
    +0.11
    0.05
    Negative Logits
    <bos>
    -1.61
     contextes
    -0.57
     repress
    -0.55
    ⓧ
    -0.55
     disarm
    -0.53
    
    
    -0.52
     dampen
    -0.52
     liker
    -0.52
     neutralize
    -0.51
     lubric
    -0.51
    POSITIVE LOGITS
     Jambi
    1.17
     Minang
    1.15
     Karang
    1.12
     Banjar
    1.12
     Pekan
    1.09
     Lampung
    1.08
     Tanjung
    1.07
     Muhamma
    1.06
     Palembang
    1.05
     silikon
    1.05
    Activations Density 1.678%

    No Known Activations