© 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. 4552
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity vulnerabilities and attacks

    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
    +0.34
    1.4%
    876
    +0.21
    0.8%
    1842
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.34
    -0.02
    946
    +0.21
    0.06
    100
    +0.17
    0.05
    Negative Logits
    <bos>
    -2.99
    lateinit
    -0.69
    amaño
    -0.63
    /***
    -0.62
    Rusia
    -0.61
     ajudá
    -0.61
    //----
    -0.58
    MockBean
    -0.58
    setClass
    -0.57
     esquecer
    -0.57
    POSITIVE LOGITS
     milano
    1.39
     frankfurt
    1.35
     bandung
    1.24
     napoli
    1.19
     munich
    1.16
     wien
    1.16
     swarovski
    1.16
     bayern
    1.15
     stockholm
    1.13
     sfera
    1.11
    Activations Density 0.998%

    No Known Activations