© 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. 3565
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and organizations in the context of news reporting

    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
    1967
    +0.09
    0.3%
    1842
    +0.09
    0.2%
    1919
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.09
    0.04
    862
    +0.09
    0.02
    2029
    +0.09
    0.03
    Negative Logits
     emphat
    -1.04
     encomp
    -1.03
     guarante
    -1.01
     gild
    -1.01
     swarovski
    -1.00
     fuf
    -0.98
     intersper
    -0.98
     indestru
    -0.97
     michelin
    -0.97
     peppa
    -0.95
    POSITIVE LOGITS
    DoubleQuotes
    0.77
     NKC
    0.66
     resides
    0.64
     chi̍t
    0.61
    Carriera
    0.59
     reside
    0.57
    IntoConstraints
    0.56
     resided
    0.56
    BeginInit
    0.55
    WithMany
    0.55
    Activations Density 0.282%

    No Known Activations