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. 22-GEMMASCOPE-RES-16K
    6. 13028
    Prev
    Next
    INDEX
    Explanations

    names of researchers and contributors involved in a project or study

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

    Chinese names (specifically, last names)

    np_acts-logits-general · gemini-2.0-flash

    Chinese names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gency
    -0.55
     createSlice
    -0.52
    LLocation
    -0.51
    OrNil
    -0.48
    ább
    -0.47
    esez
    -0.45
     EClass
    -0.43
    koin
    -0.43
     setuptools
    -0.43
    mington
    -0.42
    POSITIVE LOGITS
     Wang
    1.26
     Zhang
    1.25
     Liu
    1.22
     Chen
    1.14
     Zhou
    1.11
     Zhao
    1.11
    Wang
    1.09
     Li
    1.06
    Zhang
    1.02
    Liu
    1.02
    Activations Density 0.217%

    No Known Activations