Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7875
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Apple."

    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
    1.6%
    184
    +0.14
    0.6%
    1919
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.38
    0.10
    1097
    +0.14
    0.09
    1504
    +0.12
    0.06
    Negative Logits
    <bos>
    -2.34
     perla
    -0.73
     Seeder
    -0.72
     cristian
    -0.72
     adal
    -0.72
     solidar
    -0.71
     anse
    -0.71
     prostitu
    -0.71
    estimable
    -0.69
     augus
    -0.69
    POSITIVE LOGITS
     pymysql
    1.23
     Wtf
    1.05
     unspeak
    1.02
     psycopg
    0.98
     Lmao
    0.98
     heapq
    0.96
     pymongo
    0.93
     idéale
    0.92
     affor
    0.90
     McLaugh
    0.88
    Activations Density 0.452%

    No Known Activations