© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 667
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms related to science and academia

    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
    874
    +0.13
    0.4%
    67
    +0.10
    0.3%
    1708
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.13
    0.04
    1120
    +0.10
    0.04
    1363
    +0.09
    0.03
    Negative Logits
    /**
    -0.93
    <?
    -0.78
    /*
    -0.69
    extField
    -0.65
     gratify
    -0.64
    ⓧ
    -0.61
    
    
    -0.58
     digress
    -0.58
     stifle
    -0.57
     fend
    -0.57
    POSITIVE LOGITS
     IN
    1.24
    IN
    1.20
     montrant
    0.95
     catég
    0.90
     réunis
    0.90
     sélectionnés
    0.85
     clô
    0.83
     nommée
    0.82
     ··
    0.80
     jouant
    0.79
    Activations Density 0.254%

    No Known Activations