© 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. 14481
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical analysis and research

    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
    872
    +0.13
    0.4%
    1150
    +0.13
    0.4%
    227
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.08
    1190
    +0.13
    0.05
    1150
    +0.11
    0.02
    Negative Logits
     koc
    -0.67
     kask
    -0.67
     gesta
    -0.65
     utop
    -0.65
     plak
    -0.63
     lapto
    -0.62
     moza
    -0.60
     himo
    -0.60
    DoubleQuotes
    -0.59
     trening
    -0.58
    POSITIVE LOGITS
     aussitôt
    0.91
     quoique
    0.90
     volon
    0.87
     Dica
    0.86
    UwU
    0.85
     Áng
    0.85
     Bárbara
    0.85
     quelquefois
    0.85
     calum
    0.83
     Quien
    0.81
    Activations Density 0.702%

    No Known Activations