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. 20-GEMMASCOPE-RES-16K
    6. 9010
    Prev
    Next
    INDEX
    Explanations

    code that represents equality and hashing methods in object-oriented programming

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

    Code or numerical values

    np_acts-logits-general · gemini-2.0-flash

    public int compareTo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.66
    TagMode
    -0.66
     كومونز
    -0.63
    EndContext
    -0.56
    ChromeDriver
    -0.54
    хьтан
    -0.53
    appé
    -0.50
    bondale
    -0.49
    缀
    -0.49
    ymce
    -0.49
    POSITIVE LOGITS
     hashCode
    0.84
    hashCode
    0.83
    memoized
    0.73
    HashCode
    0.67
     hash
    0.63
    StoryboardSegue
    0.56
     Hash
    0.56
    featureID
    0.55
    LookAnd
    0.54
     prime
    0.54
    Activations Density 0.115%

    No Known Activations