© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3669
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations and government entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1741
    +0.10
    0.3%
    946
    +0.10
    0.3%
    1510
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.10
    0.05
    1499
    +0.10
    0.06
    577
    +0.10
    0.05
    Negative Logits
     vinaigrette
    -0.72
     purée
    -0.67
     keiner
    -0.63
     keinem
    -0.63
     keines
    -0.62
     demselben
    -0.62
     Casserole
    -0.61
     keinerlei
    -0.61
     welchem
    -0.60
     denselben
    -0.60
    POSITIVE LOGITS
     Juf
    1.52
     Godt
    1.51
     fta
    1.50
     Augu
    1.48
     aen
    1.45
     saar
    1.45
     mef
    1.44
     Departement
    1.44
     Ibidem
    1.42
     thut
    1.40
    Activations Density 0.308%

    No Known Activations