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. 15181
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to display screens and camera features in smartphones

    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
    +0.27
    1.0%
    1385
    +0.12
    0.5%
    876
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.27
    0.06
    1982
    +0.12
    0.04
    1411
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.57
    ⓧ
    -1.39
    
    
    -1.23
    /**
    -1.12
    <?
    -1.06
    /*
    -0.92
    <?
    
    -0.79
     intersper
    -0.74
    Transcripción
    -0.72
    /***
    
    -0.71
    POSITIVE LOGITS
     corrom
    1.01
     maroc
    0.98
     bandung
    0.97
     jawa
    0.95
     pican
    0.95
     churrasco
    0.93
     palio
    0.92
     pymysql
    0.88
     heapq
    0.87
     cioc
    0.86
    Activations Density 0.343%

    No Known Activations