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. 1-GEMMASCOPE-RES-16K
    6. 14838
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to the establishment and organization of entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OOTDTY
    -0.81
    daß
    -0.79
    GLOBALS
    -0.78
    wpdb
    -0.78
     AttributeSet
    -0.75
     ContentValues
    -0.73
    IActionResult
    -0.73
    NSNotification
    -0.72
    fseek
    -0.70
     ThemeData
    -0.70
    POSITIVE LOGITS
    osoba
    0.64
    with
    0.63
     conseguenze
    0.60
    state
    0.60
     religieuses
    0.60
    style
    0.56
     barbati
    0.53
     leggero
    0.53
    دانشنامهٔ
    0.53
    With
    0.53
    Activations Density 0.569%

    No Known Activations