© 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. 3619
    Prev
    Next
    INDEX
    Explanations

    references to different seasons, episodes, and characters in a television series

    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
    90
    +0.17
    0.6%
    1964
    +0.15
    0.5%
    1581
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.17
    0.05
    1581
    +0.15
    0.04
    1964
    +0.14
    0.05
    Negative Logits
     particolar
    -0.71
     affez
    -0.68
     accogli
    -0.67
     eccell
    -0.66
     virtù
    -0.62
    alberto
    -0.61
     pollut
    -0.59
     estrema
    -0.59
     liev
    -0.58
     espri
    -0.57
    POSITIVE LOGITS
     season
    1.38
     Season
    1.25
    Season
    1.20
    season
    1.19
     seasons
    1.14
     SEASON
    1.12
    SEASON
    1.02
     Seasons
    0.92
    seasons
    0.90
    Seasons
    0.90
    Activations Density 0.090%

    No Known Activations