© 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. 18-GEMMASCOPE-RES-16K
    11. 11253
    Prev
    Next
    INDEX
    Explanations

    phrases that convey personal thoughts or reflections

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

    "After all" or similar argumentative phrases

    np_acts-logits-general · gemini-2.0-flash

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.72
     كومونز
    -0.50
    muito
    -0.48
     naselje
    -0.48
    INCLUDED
    -0.44
     tačiau
    -0.44
    AutoScaleMode
    -0.44
    sehr
    -0.43
    ficulties
    -0.43
    ]}"
    -0.42
    POSITIVE LOGITS
     why
    1.11
     Why
    1.09
    Why
    1.05
    why
    0.98
     przecież
    0.97
     Schließlich
    0.93
     Pourquoi
    0.91
     pourquoi
    0.84
    毕竟
    0.82
    だって
    0.82
    Activations Density 0.229%

    No Known Activations