© 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. 2353
    Prev
    Next
    INDEX
    Explanations

    links to downloadable content such as e-books and recipes, particularly targeting the action of clicking, following links, and downloading PDFs

    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
    1343
    +0.29
    0.9%
    453
    +0.22
    0.7%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.29
    0.03
    1343
    +0.22
    0.02
    1786
    +0.10
    0.01
    Negative Logits
     fta
    -1.64
     ftu
    -1.64
     thut
    -1.59
     fte
    -1.52
     fep
    -1.51
     aen
    -1.51
     squa
    -1.44
     ftre
    -1.43
     fup
    -1.42
     fays
    -1.41
    POSITIVE LOGITS
    Forme
    0.56
     RoutedEventArgs
    0.51
    AUTOR
    0.50
    EndInit
    0.49
    DataPropertyName
    0.47
    Diret
    0.46
     CURLOPT
    0.46
    Gfx
    0.45
    preview
    0.45
    ServiceModel
    0.45
    Activations Density 0.044%

    No Known Activations