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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15568
    Prev
    Next
    INDEX
    Explanations

    expressions relating to economic decline and financial struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.47
     itinéraires
    -0.41
     ligiloj
    -0.41
    providedIn
    -0.41
    WindowConstants
    -0.41
    Они
    -0.40
    GOTREF
    -0.39
    而是
    -0.37
    あくまで
    -0.37
    OGND
    -0.36
    POSITIVE LOGITS
    RegressionTest
    0.53
    ngdoc
    0.51
     '\\;'
    0.47
     spalle
    0.47
    MemoryWarning
    0.45
     forze
    0.43
     frutta
    0.42
     firebaseConfig
    0.42
     sonno
    0.42
    Clik
    0.41
    Activations Density 0.406%

    No Known Activations