© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8431
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong emotional reactions or assessments, particularly related to disappointment or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mektedir
    -0.98
    INSEE
    -0.69
    maktadır
    -0.69
     CANNOT
    -0.60
    KeyEvent
    -0.60
    才可以
    -0.60
    Diweddarwch
    -0.60
    rsiniz
    -0.60
    mıştır
    -0.60
    AutoScaleMode
    -0.58
    POSITIVE LOGITS
     gotta
    1.09
     outta
    1.01
     تانيه
    1.01
     gonna
    1.00
     somethin
    0.97
     GONNA
    0.88
     talkin
    0.86
     nothin
    0.84
    Gonna
    0.82
    Gimme
    0.82
    Activations Density 0.383%

    No Known Activations