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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10338
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals and achievement

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

    preceding "goals," "objective," or "target."

    np_acts-logits-general · gemini-2.0-flash

    achieving goals or targets

    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
     виправивши
    -0.89
    AccessorTable
    -0.69
    elemField
    -0.66
    +#+#
    -0.59
     kaarangay
    -0.53
    dikan
    -0.51
     utafitiHapana
    -0.51
    yship
    -0.49
    RTGC
    -0.48
    ніципа
    -0.47
    POSITIVE LOGITS
     goals
    2.68
     goal
    2.54
     objectives
    2.31
     Goals
    2.26
    goal
    2.22
    goals
    2.19
    Goals
    2.15
     Goal
    2.11
    Goal
    2.05
     targets
    2.03
    Activations Density 0.361%

    No Known Activations