© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8205
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions and their association with relational phrases

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

    followed by "or" or "and"

    np_acts-logits-general · gemini-2.0-flash

    or and after

    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
    RTGC
    -0.42
     ceket
    -0.33
     الوا
    -0.33
    สือ
    -0.32
    kloped
    -0.31
    IU
    -0.31
     féd
    -0.30
     cassa
    -0.30
     SCC
    -0.30
    spp
    -0.30
    POSITIVE LOGITS
     MainAxisSize
    0.56
     protoimpl
    0.54
     alongside
    0.53
    يكب
    0.53
     GenerationType
    0.53
     jsPsych
    0.53
    DockStyle
    0.52
    StoryboardSegue
    0.51
    Билгалдахарш
    0.50
     AROUND
    0.50
    Activations Density 0.183%

    No Known Activations