© 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. 0-RES-JB
    11. 2591
    Prev
    Next
    INDEX
    Explanations

    mentions of different grit levels and abrasive materials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1136
    +0.08
    0.2%
    703
    +0.07
    0.2%
    750
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.08
    0.06
    1343
    +0.07
    0.06
    283
    +0.07
    0.01
    Negative Logits
     =[]
    -0.60
    relenting
    -0.59
    Siti
    -0.59
     shuddered
    -0.57
     strto
    -0.57
    pejo
    -0.57
    Londres
    -0.56
     perguntou
    -0.54
     nmax
    -0.54
     assholes
    -0.54
    POSITIVE LOGITS
    gif
    1.03
     GIF
    1.00
     grit
    1.00
     gif
    0.98
    grit
    0.98
    CTL
    0.92
    GIF
    0.91
     cioc
    0.91
     gifs
    0.87
     grits
    0.84
    Activations Density 0.413%

    No Known Activations