© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 172
    Prev
    Next
    INDEX
    Explanations

    words that convey strong emotional states or actions

    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
    +0.22
    0.9%
    478
    +0.15
    0.7%
    1177
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.22
    0.06
    1763
    +0.15
    0.06
    1415
    +0.10
    0.05
    Negative Logits
    <bos>
    -1.49
     intersper
    -1.38
     endow
    -1.02
     rouse
    -0.86
    /***
    -0.80
     acquaint
    -0.80
     overcrow
    -0.80
     allude
    -0.79
     banish
    -0.78
     quitted
    -0.76
    POSITIVE LOGITS
    haustible
    0.98
    ureusement
    0.91
    viously
    0.90
    lably
    0.88
    requently
    0.86
    ligently
    0.83
    pection
    0.82
    limsy
    0.82
     blackpink
    0.82
    quently
    0.80
    Activations Density 0.246%

    No Known Activations