© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1298
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms related to data processing and systems management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text before questions or certain surnames

    np_acts-logits-general · gemini-2.0-flash

    following or subsequent events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.55
    rull
    -0.55
    awtextra
    -0.54
    didSet
    -0.51
    czegó
    -0.50
     InputDecoration
    -0.49
    jooq
    -0.49
    ASX
    -0.48
    }();
    -0.47
    GIVEREF
    -0.46
    POSITIVE LOGITS
     afterwards
    1.85
     thereafter
    1.83
     afterward
    1.73
     subsequent
    1.50
     subsequently
    1.50
     later
    1.40
     Afterwards
    1.39
     Thereafter
    1.36
    Afterwards
    1.36
     successivo
    1.27
    Activations Density 1.043%

    No Known Activations