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. 1643
    Prev
    Next
    INDEX
    Explanations

    locations and names of towns or places

    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
    394
    +0.22
    0.7%
    1343
    +0.17
    0.5%
    1978
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.22
    0.06
    981
    +0.17
    0.05
    1235
    +0.15
    0.04
    Negative Logits
    <bos>
    -1.28
    fromnode
    -0.98
     kasarigan
    -0.96
    GEBURTSDATUM
    -0.90
     autorytatywna
    -0.85
     invokingState
    -0.83
    IndentedString
    -0.82
    oredCriteria
    -0.81
    kháu
    -0.80
    localctx
    -0.80
    POSITIVE LOGITS
     compen
    2.00
     unden
    1.89
     deleter
    1.83
     emphat
    1.81
     embodi
    1.80
     uniqu
    1.77
     suscep
    1.74
     inev
    1.74
     unve
    1.73
     embra
    1.73
    Activations Density 0.212%

    No Known Activations