© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10175
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and control

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

    Follows the word "under" indicating a state of control or influence

    np_acts-logits-general · gemini-2.0-flash

    under the

    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
    AllowUser
    -0.46
     ziua
    -0.45
    省市镇
    -0.44
     insides
    -0.43
    avenir
    -0.43
    ähän
    -0.42
     OMITBAD
    -0.42
     useRouter
    -0.41
    #+#
    -0.41
    INCLUDED
    -0.41
    POSITIVE LOGITS
     auspices
    1.39
     supervision
    1.17
     aegis
    1.15
     guise
    1.09
     watchful
    1.08
     umbrella
    1.06
     ausp
    0.98
     tute
    0.96
     guidance
    0.94
    umbrella
    0.92
    Activations Density 0.213%

    No Known Activations