© 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. 896
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location or organization

    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
    50
    +0.10
    0.4%
    1677
    +0.07
    0.3%
    381
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.05
    144
    +0.07
    0.04
    511
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.07
     fået
    -0.82
    SPECTION
    -0.75
     gøre
    -0.75
    anyuan
    -0.74
     nadzie
    -0.72
     nadzieję
    -0.72
    public
    -0.71
     blive
    -0.71
    Ngoài
    -0.71
    POSITIVE LOGITS
     délib
    1.75
     catég
    1.65
     habile
    1.64
     véhic
    1.60
     quoique
    1.57
     soulign
    1.56
     déliv
    1.53
     rafra
    1.52
     prétend
    1.50
     Intere
    1.48
    Activations Density 0.195%

    No Known Activations