© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4325
    Prev
    Next
    INDEX
    Explanations

    words related to blood or bloody imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.13
    0.6%
    678
    +0.12
    0.5%
    1339
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.13
    0.06
    1343
    +0.12
    0.06
    1056
    +0.12
    0.04
    Negative Logits
     unspeak
    -1.55
     impelled
    -1.47
     endeavouring
    -1.43
     ujedno
    -1.39
     vainly
    -1.26
     endeavored
    -1.26
     ardour
    -1.18
     assailed
    -1.13
     quitted
    -1.13
     hastened
    -1.13
    POSITIVE LOGITS
     pluri
    1.12
     Komple
    1.07
     gymnas
    1.06
     klu
    1.05
     LUMI
    1.05
     turbul
    1.01
     Blo
    0.99
     emble
    0.99
     knap
    0.97
     pyram
    0.97
    Activations Density 0.230%

    No Known Activations