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. 10-RES-JB
    6. 1016
    Prev
    Next
    INDEX
    Explanations

    geographic locations or place names

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.18
    0.7%
    1842
    +0.12
    0.5%
    964
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.18
    0.04
    870
    +0.12
    0.03
    283
    +0.12
    0.01
    Negative Logits
    <bos>
    -2.13
    ⓧ
    -0.81
    },[])
    -0.68
    HasIndex
    -0.67
    <>
    
    -0.65
    /**
    -0.65
    <?
    -0.65
    ždý
    -0.65
    
    
    -0.64
    //
    -0.64
    POSITIVE LOGITS
     fta
    1.76
     ftu
    1.72
     „,
    1.66
     mef
    1.65
     hcm
    1.64
     aen
    1.64
     wien
    1.60
     ftre
    1.57
     Juf
    1.57
     wikihow
    1.55
    Activations Density 0.088%

    No Known Activations