© 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. 191
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific object used for sitting or riding, especially in relation to outdoor activities like climbing or horseback riding

    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
    805
    +0.10
    0.3%
    67
    +0.08
    0.2%
    1194
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.04
    184
    +0.08
    0.01
    1120
    +0.08
    0.03
    Negative Logits
    <bos>
    -0.80
    millimeters
    -0.64
    providedIn
    -0.64
    IMPORTED
    -0.63
    RTEX
    -0.61
     &___
    -0.60
    numerusform
    -0.59
     تضيفلها
    -0.58
    thâu
    -0.57
    стьян
    -0.56
    POSITIVE LOGITS
     saddle
    1.50
     Saddle
    1.45
     saddles
    1.32
     impra
    1.21
     shenan
    1.20
     Ranch
    1.20
     lmfao
    1.20
     jaya
    1.19
     rodriguez
    1.19
     affor
    1.14
    Activations Density 0.280%

    No Known Activations