© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quotes or thoughts in quotation marks

    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
    1323
    +0.15
    0.5%
    1265
    +0.12
    0.4%
    1842
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.15
    0.05
    1265
    +0.12
    0.05
    257
    +0.11
    0.05
    Negative Logits
     fta
    -1.79
     squa
    -1.71
     fte
    -1.70
     aen
    -1.66
     secon
    -1.63
     volunte
    -1.60
     increa
    -1.60
     ftu
    -1.60
     guarante
    -1.60
     purcha
    -1.59
    POSITIVE LOGITS
    ,”
    0.93
    ,"
    0.85
     which
    0.77
     though
    0.74
    ,’
    0.73
    ，“
    0.73
    ，”
    0.70
    ”，
    0.68
     but
    0.68
    thinkable
    0.67
    Activations Density 0.196%

    No Known Activations