© 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. 10-RES-JB
    11. 2931
    Prev
    Next
    INDEX
    Explanations

    assertions related to the authenticity and credibility of a brand

    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
    50
    +0.20
    0.6%
    1013
    +0.09
    0.3%
    871
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1738
    +0.20
    0.04
    310
    +0.09
    0.04
    632
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.12
    char
    -0.74
    lateinit
    -0.69
     da
    -0.68
     das
    -0.67
    .
    -0.66
    ,
    -0.66
    อ
    -0.65
     are
    -0.65
     vai
    -0.64
    POSITIVE LOGITS
     maneu
    1.75
     eiffel
    1.70
     viciss
    1.69
     indestru
    1.69
     bandung
    1.68
     bordeaux
    1.67
     excru
    1.67
     increa
    1.67
     inev
    1.65
     swarovski
    1.65
    Activations Density 0.265%

    No Known Activations