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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 340
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Memphis" and related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    370
    +0.09
    0.3%
    897
    +0.08
    0.3%
    889
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.09
    0.05
    1735
    +0.08
    0.04
    1252
    +0.08
    0.04
    Negative Logits
    ⓧ
    -0.80
    /*
    -0.77
    /**
    -0.73
     put
    -0.73
    ുറ
    -0.70
     qu
    -0.69
    ਼
    -0.68
     й
    -0.67
    וכ
    -0.67
     get
    -0.67
    POSITIVE LOGITS
     wien
    2.05
     Juf
    2.00
     maneu
    1.94
     lele
    1.87
     fta
    1.86
     invin
    1.85
     aen
    1.82
     perfet
    1.81
     increa
    1.80
     stockholm
    1.80
    Activations Density 0.234%

    No Known Activations