© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    references to economic indicators and trends

    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
    1013
    +0.12
    0.4%
    2034
    +0.12
    0.3%
    1253
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.12
    0.03
    1720
    +0.12
    0.02
    1605
    +0.10
    0.01
    Negative Logits
     encomp
    -1.62
     volunte
    -1.58
     resear
    -1.56
     effe
    -1.55
     opport
    -1.55
     emphat
    -1.54
     philanth
    -1.54
     inev
    -1.52
     reluct
    -1.51
     Mlle
    -1.51
    POSITIVE LOGITS
    .
    0.77
     due
    0.73
    。
    0.65
    due
    0.64
    ;
    0.62
    ↵↵
    0.62
    ,
    0.62
     levels
    0.61
     thanks
    0.60
     and
    0.60
    Activations Density 0.200%

    No Known Activations