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. 17-GEMMASCOPE-RES-16K
    6. 7323
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical and medical abbreviations or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onAnimation
    -0.57
     userSchema
    -0.57
    InputBorder
    -0.54
     onCreateView
    -0.54
    ffffffff
    -0.51
     façons
    -0.51
     actionMode
    -0.50
     Touchable
    -0.50
     onPostExecute
    -0.50
     PASSWORD
    -0.49
    POSITIVE LOGITS
     ++)
    0.72
     PSOE
    0.69
     СПб
    0.65
     NYPD
    0.65
     MD
    0.65
    GOTREF
    0.64
    featureID
    0.64
     MS
    0.63
    Rptr
    0.62
     MLB
    0.61
    Activations Density 1.378%

    No Known Activations