© 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. 2495
    Prev
    Next
    INDEX
    Explanations

    terms related to injuries and damage

    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
    +0.18
    0.7%
    1385
    +0.17
    0.6%
    946
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.18
    0.08
    946
    +0.17
    0.07
    468
    +0.14
    0.05
    Negative Logits
    <bos>
    -2.43
    HasAnnotation
    -0.92
    |}
    -0.82
    public
    -0.81
    //
    -0.80
    /**
    -0.78
    ///
    -0.76
    /**
    -0.74
    }
    -0.74
    <!--
    -0.73
    POSITIVE LOGITS
     Juf
    1.98
     Augu
    1.78
     maneu
    1.70
     hcm
    1.65
     emphat
    1.63
     Intere
    1.62
     sovere
    1.61
     stockholm
    1.61
     Confu
    1.60
     reluct
    1.56
    Activations Density 0.344%

    No Known Activations