© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 16177
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and protocols in the context of development and systems

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

    Followed by "called," "known," or similar words

    np_acts-logits-general · gemini-2.0-flash

    concepts called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.82
    KURZBESCHREIBUNG
    -0.77
     propOrder
    -0.74
    MessageTagHelper
    -0.68
     }}"></
    -0.68
    WithIOException
    -0.66
    ंदीखरीदारी
    -0.64
    PreAuthorize
    -0.62
    "]]
    -0.62
    "]}
    -0.61
    POSITIVE LOGITS
     called
    2.93
    called
    2.60
     Called
    2.44
     llamado
    2.40
    Called
    2.36
     chamado
    2.27
     CALLED
    2.25
     llamada
    2.22
     chamada
    2.18
     termed
    2.13
    Activations Density 0.993%

    No Known Activations