Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3686
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" and its variations

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

    "join" or its variations

    np_acts-logits-general · gemini-2.0-flash

    joining and inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UnityEngine
    -0.45
     Abstracts
    -0.40
     Negra
    -0.39
    nocache
    -0.38
     extrema
    -0.38
     kró
    -0.38
     PeEnEo
    -0.38
    ')")
    -0.37
     MutableLiveData
    -0.37
     negra
    -0.36
    POSITIVE LOGITS
    join
    1.39
     join
    1.38
     Join
    1.30
    Join
    1.27
     JOIN
    1.25
     Joining
    1.21
     joining
    1.21
    Joining
    1.19
    joining
    1.18
     joined
    1.17
    Activations Density 0.074%

    No Known Activations