© 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. 3498
    Prev
    Next
    INDEX
    Explanations

    terms related to locations and infrastructure

    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
    1978
    +0.13
    0.4%
    297
    +0.12
    0.4%
    453
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.13
    0.03
    1597
    +0.12
    0.03
    1935
    +0.11
    0.03
    Negative Logits
     translateY
    -0.55
    Dichloroethene
    -0.53
    Grüße
    -0.51
    blockList
    -0.51
    BeforeAll
    -0.50
    netinet
    -0.50
    TableField
    -0.49
    KEYCODE
    -0.49
     ২০
    -0.49
     recrystal
    -0.48
    POSITIVE LOGITS
     keramik
    0.99
     kram
    0.97
    fordable
    0.95
     silikon
    0.94
     antik
    0.94
     panik
    0.94
     ekos
    0.93
     kafe
    0.90
     konsult
    0.90
     kompres
    0.89
    Activations Density 0.091%

    No Known Activations