© 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. 13886
    Prev
    Next
    INDEX
    Explanations

    information related to ratios, specifically between different quantities or values

    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
    1306
    +0.14
    0.5%
    1993
    +0.11
    0.4%
    1581
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1306
    +0.14
    0.02
    390
    +0.11
    0.01
    437
    +0.11
    0.01
    Negative Logits
     tind
    -1.00
     Hez
    -0.94
     Epif
    -0.93
     Amé
    -0.91
     Perci
    -0.87
     Câ
    -0.86
     Obre
    -0.85
     Vn
    -0.85
     Mlle
    -0.84
     adh
    -0.84
    POSITIVE LOGITS
     ratio
    1.51
     ratios
    1.39
    ratio
    1.33
     Ratio
    1.30
    Ratio
    1.21
     Ratios
    1.13
     RATIO
    1.09
    ratios
    0.99
    RATIO
    0.93
     ration
    0.78
    Activations Density 0.065%

    No Known Activations