© 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. 1-GEMMASCOPE-RES-16K
    6. 8826
    Prev
    Next
    INDEX
    Explanations

    references to the term "morphological" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoField
    -0.35
    zarchiwizowane
    -0.35
    GeneratedValue
    -0.33
    ManyToMany
    -0.31
    demie
    -0.30
     сбо
    -0.28
    ventud
    -0.28
     Jacek
    -0.28
     synchronized
    -0.28
     McGuire
    -0.28
    POSITIVE LOGITS
     mor
    2.94
     Mor
    2.91
    Mor
    2.88
    mor
    2.83
    MOR
    2.56
     MOR
    2.55
     morph
    2.16
    morph
    2.14
     Morph
    2.02
    Morph
    1.98
    Activations Density 0.252%

    No Known Activations