© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 9645
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions or states of being in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     différences
    -0.56
    SuccessListener
    -0.51
    ="@+
    -0.51
    gulama
    -0.49
     polegadas
    -0.49
    ētu
    -0.48
    etheless
    -0.47
     صوتيه
    -0.47
     sogget
    -0.47
    mainloop
    -0.46
    POSITIVE LOGITS
    $_['
    0.77
    MemoryWarning
    0.77
     NSCoder
    0.74
    parsedMessage
    0.66
    +#+#
    0.65
    RegistryLite
    0.65
     <>",
    0.62
    évaluateur
    0.60
    contentLoaded
    0.59
    HtmlAttribute
    0.58
    Activations Density 0.359%

    No Known Activations