© 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. 14213
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and demands in a challenging context

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

    Following common negative words (not, any, a, that)

    np_acts-logits-general · gemini-2.0-flash

    any harm

    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
    setVerticalGroup
    -0.83
    ^(@)
    -0.77
     nahilalakip
    -0.74
    +#+#
    -0.74
    ]--;
    -0.72
     mum
    -0.67
     الحره
    -0.65
    itinéraire
    -0.65
    ########.
    -0.63
    Kjelder
    -0.62
    POSITIVE LOGITS
     cotone
    0.48
     metálico
    0.43
    évaluateur
    0.43
     AppModule
    0.42
    TemporalType
    0.42
     bénéfice
    0.42
     bob
    0.42
     Trotter
    0.42
     toer
    0.41
     gorra
    0.41
    Activations Density 0.160%

    No Known Activations