© 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. 0-RES-JB
    11. 2317
    Prev
    Next
    INDEX
    Explanations

    mentions of military operations and military personnel

    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
    1763
    +0.08
    0.2%
    1334
    +0.08
    0.2%
    421
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.08
    0.04
    690
    +0.08
    0.04
    184
    +0.07
    0.01
    Negative Logits
     @"/
    -0.70
     dis
    -0.66
    Karakteristik
    -0.66
    mybatisplus
    -0.62
    FieldDescriptor
    -0.60
    +:+
    -0.59
    synthesize
    -0.58
    para
    -0.58
     para
    -0.57
    ционер
    -0.56
    POSITIVE LOGITS
     Juf
    1.59
     shenan
    1.59
     Shakspeare
    1.49
     disagre
    1.49
     maneu
    1.46
     fta
    1.42
     embodi
    1.41
     depic
    1.38
     beaute
    1.34
     »>
    1.34
    Activations Density 0.317%

    No Known Activations