© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6494
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific organizations or individuals involved in international affairs

    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
    +0.17
    0.6%
    455
    +0.07
    0.2%
    316
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.06
    455
    +0.07
    0.02
    283
    +0.06
    -0.00
    Negative Logits
    <bos>
    -2.52
     Godt
    -0.77
     herre
    -0.70
     Vå
    -0.70
    CPtr
    -0.70
    Etter
    -0.68
     Kø
    -0.67
     Meksiku
    -0.67
    Kjelder
    -0.66
     LCCN
    -0.64
    POSITIVE LOGITS
     unwarran
    1.76
     impractica
    1.49
     McLaugh
    1.48
     sovere
    1.48
     affor
    1.47
     unlaw
    1.46
     embodi
    1.45
     quoique
    1.43
     philanth
    1.43
     reluct
    1.43
    Activations Density 0.446%

    No Known Activations