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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 46
    Prev
    Next
    INDEX
    Explanations

    terms related to changes and transformations in concepts or states

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

    verbs and adjectives that convey a sense of transformation or change.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi

    scientific or technical language involving complex processes and interactions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    copg
    -0.61
    addCriterion
    -0.57
    IntentFilter
    -0.56
     Gunakan
    -0.55
     Walkover
    -0.53
    Enllaços
    -0.52
    Bibitem
    -0.52
    AddTagHelper
    -0.52
    fromnode
    -0.52
    ElementException
    -0.51
    POSITIVE LOGITS
     us
    0.54
    TagMode
    0.35
     me
    0.35
     you
    0.35
     our
    0.32
     brings
    0.32
     the
    0.30
     motivates
    0.30
     gyhoeddwyd
    0.30
     inspires
    0.29
    Activations Density 0.308%

    No Known Activations