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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 159
    Prev
    Next
    INDEX
    Explanations

    terms related to insect control and entomology

    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
    161
    +0.09
    0.3%
    645
    +0.09
    0.3%
    1605
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1709
    +0.09
    0.03
    894
    +0.09
    0.03
    1405
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.09
    makeText
    -0.67
     defaultstate
    -0.64
    glDelete
    -0.63
    CopyWith
    -0.63
    namespace
    -0.61
    MarshalTo
    -0.60
    WriteAttribute
    -0.60
    HandleFunc
    -0.60
    AddAttribute
    -0.59
    POSITIVE LOGITS
     insect
    1.88
     insects
    1.83
     Insect
    1.65
    Insect
    1.59
    insect
    1.57
     Insects
    1.56
     pest
    1.47
     bugs
    1.47
     pests
    1.38
     Pest
    1.33
    Activations Density 0.194%

    No Known Activations