© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 5122
    Prev
    Next
    INDEX
    Explanations

    information about resources, references, or data sources

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.1%
    1150
    +0.12
    0.4%
    227
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.30
    0.03
    1143
    +0.12
    0.04
    1799
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.13
    FailureListener
    -0.67
    LayoutStyle
    -0.64
    OneToMany
    -0.64
    PathParam
    -0.63
    Sqft
    -0.62
    setDo
    -0.61
    /**
    -0.60
    FieldDescriptor
    -0.60
    HasIndex
    -0.60
    POSITIVE LOGITS
     accla
    2.13
     maneu
    2.11
     impra
    2.02
     reluct
    2.01
     excru
    1.88
     affor
    1.86
     disagre
    1.86
     increa
    1.84
     inconce
    1.84
     inev
    1.82
    Activations Density 0.339%

    No Known Activations