© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 4171
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts and command sequences related to software functions

    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%
    1343
    +0.13
    0.5%
    876
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1661
    +0.22
    0.02
    678
    +0.13
    0.02
    778
    +0.10
    0.01
    Negative Logits
    <bos>
    -3.06
    SourceChecksum
    -0.84
    Parcelize
    -0.74
    Autoritní
    -0.73
    RegressionTest
    -0.73
    dataclass
    -0.73
    HtmlAttribute
    -0.73
    MergeFrom
    -0.72
    </thead>
    -0.72
    FieldDescriptor
    -0.72
    POSITIVE LOGITS
     affor
    1.92
     maneu
    1.90
     stockholm
    1.89
     eiffel
    1.85
     lidl
    1.81
     frankfurt
    1.80
     scrat
    1.75
     disreg
    1.74
     impra
    1.73
     ecru
    1.73
    Activations Density 0.089%

    No Known Activations