© 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. 17-GEMMASCOPE-RES-16K
    6. 6906
    Prev
    Next
    INDEX
    Explanations

    concepts related to reality checks and self-awareness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ใจ
    -0.45
     ģ
    -0.45
    dington
    -0.43
     referenties
    -0.42
    Jeografia
    -0.42
    pitch
    -0.41
    telli
    -0.41
     Fein
    -0.41
    expandindo
    -0.41
     banderas
    -0.41
    POSITIVE LOGITS
     reality
    1.45
    Reality
    1.30
     Reality
    1.24
    reality
    1.23
     realism
    1.18
     realities
    1.13
     realista
    1.07
     realist
    1.06
     realistic
    1.06
     grounded
    0.99
    Activations Density 0.163%

    No Known Activations