Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6420
    Prev
    Next
    INDEX
    Explanations

    mentions of international relations and diplomatic activities related to security and policy decisions

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.7%
    1842
    +0.11
    0.4%
    604
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    483
    +0.20
    0.05
    1759
    +0.11
    0.05
    1710
    +0.10
    0.05
    Negative Logits
    <bos>
    -3.62
    ⓧ
    -0.71
     mergeFrom
    -0.70
     initComponents
    -0.65
    MergeFrom
    -0.64
     manage
    -0.60
    assign
    -0.57
    GEBURTSDATUM
    -0.56
    💼
    -0.56
     reunite
    -0.56
    POSITIVE LOGITS
     santiago
    1.44
     sergio
    1.21
     bandung
    1.21
     pican
    1.20
     jorge
    1.19
     quegli
    1.19
     mallorca
    1.18
     ibiza
    1.17
     napoli
    1.15
     javier
    1.13
    Activations Density 0.423%

    No Known Activations