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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 8882
    Prev
    Next
    INDEX
    Explanations

    locations, departments, or contact 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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    1.1%
    31
    +0.12
    0.8%
    1870
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.18
    0.03
    421
    +0.12
    0.02
    1763
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.03
    ⓧ
    -1.10
    /**
    -0.97
    <?
    -0.88
    
    
    -0.86
    /***
    
    -0.83
     endow
    -0.79
    <?
    
    -0.79
    /*
    -0.79
     intersper
    -0.76
    POSITIVE LOGITS
     station
    1.44
     Station
    1.41
     STATION
    1.35
     Stations
    1.31
    Station
    1.28
     stations
    1.25
    station
    1.21
    stations
    1.14
    STATION
    1.12
    Stations
    1.10
    Activations Density 0.062%

    No Known Activations