© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4799
    Prev
    Next
    INDEX
    Explanations

    elements related to social justice and community dynamics

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

    preceding past-tense verbs

    np_acts-logits-general · gemini-2.0-flash

    people acting and interacting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }))
    -0.52
    DeleteBehavior
    -0.46
     obstante
    -0.44
     ört
    -0.43
    tvguidetime
    -0.43
    렵
    -0.43
     alvor
    -0.43
    cellona
    -0.43
     appartiennent
    -0.43
    estimable
    -0.43
    POSITIVE LOGITS
     acted
    1.37
     kept
    1.33
     tended
    1.30
     looked
    1.26
     worked
    1.25
     interacted
    1.25
     played
    1.24
     waited
    1.22
     dealt
    1.22
     stayed
    1.21
    Activations Density 1.247%

    No Known Activations