© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6641
    Prev
    Next
    INDEX
    Explanations

    information about wound care and medical conditions related to wound healing

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1937
    +0.21
    1.1%
    489
    +0.14
    0.8%
    406
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.21
    0.05
    1363
    +0.14
    0.04
    1013
    +0.14
    0.06
    Negative Logits
    <bos>
    -1.18
     дописавши
    -0.72
    imab
    -0.58
     handels
    -0.57
    Thiết
    -0.56
    toHaveBeen
    -0.56
     linear
    -0.55
    DockStyle
    -0.55
    randomUUID
    -0.54
     tev
    -0.53
    POSITIVE LOGITS
     burberry
    1.16
     indescri
    1.12
     ralph
    1.10
     nmax
    1.10
     inconce
    1.10
     sergio
    1.08
     impra
    1.08
     jurassic
    1.07
     swarovski
    1.07
     pcx
    1.06
    Activations Density 0.631%

    No Known Activations