© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 546
    Prev
    Next
    INDEX
    Explanations

    instances of the contraction "you've" and its variations

    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
    478
    +0.23
    1.2%
    2019
    +0.19
    1.0%
    1896
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.23
    0.14
    1224
    +0.19
    0.09
    1108
    +0.13
    0.11
    Negative Logits
    <bos>
    -3.12
    ⓧ
    -1.22
    <?
    -1.07
    
    -0.99
    /***
    -0.96
    /**
    -0.95
     Messieurs
    -0.92
     hentai
    -0.91
     regardant
    -0.90
     springfox
    -0.89
    POSITIVE LOGITS
     seksi
    0.68
    ’
    0.65
    mathrm
    0.61
    ()")
    0.61
    .='
    0.61
    )$/,
    0.60
    ]='
    0.60
    +");
    0.60
    '
    0.59
    LEMMA
    0.59
    Activations Density 0.544%

    No Known Activations