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

    Neuronpedia

    Jacobian LensNEW
    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. 295
    Prev
    Next
    INDEX
    Explanations

    mentions of physical injuries or medical emergencies, specifically bleeding occurrences

    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
    410
    +0.09
    0.3%
    1921
    +0.07
    0.2%
    1573
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.09
    0.03
    690
    +0.07
    0.03
    1343
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.99
     attach
    -0.60
     ніж
    -0.60
     put
    -0.59
     want
    -0.58
    WSER
    -0.58
     have
    -0.58
     create
    -0.57
    <blockquote>
    -0.57
     raise
    -0.57
    POSITIVE LOGITS
     wien
    1.49
     aen
    1.46
     mef
    1.45
     fta
    1.44
     franz
    1.42
     squa
    1.42
     ftu
    1.40
     sii
    1.40
     fup
    1.40
     „,
    1.39
    Activations Density 0.198%

    No Known Activations