© 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. 4109
    Prev
    Next
    INDEX
    Explanations

    instructions or guidance related to processes and 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
    +0.28
    1.0%
    752
    +0.12
    0.4%
    1978
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    758
    +0.28
    0.03
    1879
    +0.12
    0.03
    689
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.71
     did
    -0.78
     also
    -0.72
    didSet
    -0.71
    </tbody>
    -0.70
     gave
    -0.68
     had
    -0.68
     has
    -0.66
     took
    -0.66
     may
    -0.65
    POSITIVE LOGITS
     bandung
    2.13
     beverly
    1.85
     jawa
    1.83
     Juf
    1.82
     stockholm
    1.81
     swarovski
    1.81
     Minang
    1.80
     santiago
    1.80
     lele
    1.80
     fernando
    1.79
    Activations Density 0.368%

    No Known Activations