© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4506
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude towards anonymous reviewers and comments that emphasize privacy and anonymity in feedback

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

    anonymity or being anonymous

    np_acts-logits-general · gemini-2.0-flash

    anonymous or unknown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.58
    rrggbb
    -0.51
    IVEREF
    -0.48
    LabelTagHelper
    -0.46
     Administrativna
    -0.46
    enderror
    -0.44
    ChildScrollView
    -0.43
     utafitiHapana
    -0.43
     surla
    -0.42
    InjectMocks
    -0.42
    POSITIVE LOGITS
     anonymous
    2.23
     anonymity
    1.94
     Anonymous
    1.92
     anonymously
    1.92
    anonymous
    1.84
    Anonymous
    1.84
     anonim
    1.83
    匿名
    1.78
     anonyme
    1.75
     anony
    1.66
    Activations Density 0.377%

    No Known Activations