© 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. 4488
    Prev
    Next
    INDEX
    Explanations

    phrases related to memory retention and storytelling

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

    Adverbs and prepositions of direction/motion

    np_acts-logits-general · gemini-2.0-flash

    movement or completion followed by prepositions

    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
    __*/
    -0.55
    الحياه
    -0.54
    évaluateur
    -0.52
    "])
    -0.51
    EndProject
    -0.51
     "..\..\..\
    -0.47
    "))
    -0.45
    fromnode
    -0.45
    "]
    -0.45
    randomUUID
    -0.45
    POSITIVE LOGITS
     alive
    0.46
    ConstraintMaker
    0.43
    CopyWith
    0.43
     Оно
    0.42
     haline
    0.40
    IsMutable
    0.39
    paced
    0.39
     Pemer
    0.38
     relative
    0.38
    ChildScrollView
    0.38
    Activations Density 0.322%

    No Known Activations