© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 624
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ca", which likely relates to calcium

    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
    1141
    +0.14
    0.9%
    395
    +0.14
    0.9%
    1565
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.14
    0.03
    1141
    +0.14
    0.03
    1565
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.04
     harmonize
    -0.67
    ⓧ
    -0.66
    مصادر
    -0.62
     endow
    -0.56
     unify
    -0.55
     disbur
    -0.54
     embraced
    -0.54
     intersper
    -0.54
     renew
    -0.53
    POSITIVE LOGITS
     Ca
    1.23
     ca
    1.14
    Ca
    1.11
     kafe
    1.09
     kaos
    1.01
     Calcium
    1.01
     karton
    0.98
    ca
    0.98
     balkon
    0.97
     caul
    0.96
    Activations Density 0.081%

    No Known Activations