Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10681
    Prev
    Next
    INDEX
    Explanations

    indications of objectives or aims within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pee
    -0.67
    Caro
    -0.66
    дыду
    -0.63
     mug
    -0.60
    сылкі
    -0.60
     MotionEvent
    -0.59
     Caro
    -0.57
     phonon
    -0.57
     Mui
    -0.56
     wept
    -0.55
    POSITIVE LOGITS
    @[+][
    0.76
    ViewImports
    0.75
    /**
    0.72
    }`).
    0.69
    okovic
    0.69
    ]');
    0.66
    JspWriter
    0.66
     calendriers
    0.65
    omiast
    0.65
    ]),
    
    0.65
    Activations Density 0.335%

    No Known Activations