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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 344
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a difference or impact in various contexts

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

    The token "sense" appears multiple times, within the context of making a difference, indicating a focus on significance and impact. Additionally, the phrase "make a difference" is frequently associated with positive or impactful actions or decisions.

    eleuther_acts_top20 · gpt-3.5-turboTriggered by @johnny
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.39
    abestanden
    -1.29
     Roskov
    -1.23
     snippetHide
    -1.19
    GraphicsUnit
    -1.13
    DeleteBehavior
    -1.10
     AssemblyProduct
    -1.05
    AndEndTag
    -1.04
    PhysRevD
    -1.03
    MemoryWarning
    -1.02
    POSITIVE LOGITS
    ,
    0.67
     
    0.54
    ↵↵
    0.53
     and
    0.52
     …
    0.48
    or
    0.48
     to
    0.48
     '
    0.46
     on
    0.46
    .
    0.46
    Activations Density 1.588%

    No Known Activations