© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13720
    Prev
    Next
    INDEX
    Explanations

    words related to Germany and political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    172
    +0.15
    0.5%
    1520
    +0.11
    0.4%
    1177
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.15
    0.04
    1310
    +0.11
    0.03
    1837
    +0.11
    0.04
    Negative Logits
     Städ
    -1.37
     Schloß
    -1.25
     Distrikt
    -1.12
     Ewig
    -1.10
     Fürst
    -1.09
     Rathaus
    -1.07
     Freiw
    -1.07
     Orgel
    -1.05
     Leinwand
    -1.04
     Zeits
    -1.04
    POSITIVE LOGITS
     Confu
    1.76
     unwarran
    1.70
     Daven
    1.69
     increa
    1.66
     Rine
    1.64
     McLaugh
    1.62
     McInt
    1.62
     Vaugh
    1.60
     Áng
    1.58
     Juf
    1.58
    Activations Density 0.108%

    No Known Activations