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. 7873
    Prev
    Next
    INDEX
    Explanations

    structured data, particularly related to addresses and suite information

    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
    +0.28
    0.9%
    1343
    +0.18
    0.6%
    1967
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.28
    0.02
    1148
    +0.18
    0.02
    1857
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.54
    
    
    -0.93
    ⓧ
    -0.93
    /**
    -0.87
    /*
    -0.79
    <?
    -0.77
     overcrow
    -0.77
     prioritise
    -0.74
     conjure
    -0.71
     intersper
    -0.70
    POSITIVE LOGITS
     silikon
    1.23
     lele
    1.22
     mikrofon
    1.20
     saar
    1.20
     antik
    1.14
     alkoh
    1.14
     karton
    1.13
     makro
    1.12
     Kategor
    1.12
     Lombar
    1.09
    Activations Density 0.024%

    No Known Activations